{
  "scope": "公开原文归档元数据；PDF未公开镜像",
  "originals": [
    {
      "id": "arxiv-2610.02204",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.02204v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.02204v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.02204v1",
      "sha256": "93feecda4aa9f514398bf49f8e6494173cbfee6a6f6ca5e34520b1dd46efbffa",
      "bytes": 8626170,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:32:28.852010+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.02204v1",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.02204v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.02204v1",
      "pages": 17,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents",
      "sourceVersion": "2610.02204v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.151338+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.02204v1"
    },
    {
      "id": "arxiv-2610.02196",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.02196v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.02196v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.02196v1",
      "sha256": "37e61f9f5a3b7daa9d09ced06b8e72537b4815afe1cc4ee1f1a10c0bf897542b",
      "bytes": 11868445,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:32:29.060061+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.02196v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.02196v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.02196v1",
      "pages": 31,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation",
      "sourceVersion": "2610.02196v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.164776+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.02196v1"
    },
    {
      "id": "arxiv-2610.02170",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.02170v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.02170v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.02170v1",
      "sha256": "79d41ca531a2b8df3f7f935ba455bc2445ff52ba493dcce5fd8dbe6d61eec045",
      "bytes": 5929632,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:32:28.852783+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.02170v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.02170v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.02170v1",
      "pages": 17,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Watch, Infer, Coordinate: Inferring Robot Partner Constraints for Zero-Shot Coordination",
      "sourceVersion": "2610.02170v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.173482+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.02170v1"
    },
    {
      "id": "arxiv-2610.02161",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.02161v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.02161v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.02161v1",
      "sha256": "058e0c6846bc17821a0fb12190f7f61ec3a5f35a0a290d3c12cf546f7aa4aee2",
      "bytes": 10966437,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:32:39.555501+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.02161v1",
      "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.02161v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.02161v1",
      "pages": 19,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "DuoMind: Enabling Distributed Multi-Robot Coordination with Semantic Communication",
      "sourceVersion": "2610.02161v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.186553+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.02161v1"
    },
    {
      "id": "arxiv-2610.02120",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.02120v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.02120v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.02120v1",
      "sha256": "2518572d4baff871b3667fb5d22fd171f89ee6e87f192697a4e86f872adc4e49",
      "bytes": 3680379,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:32:39.475002+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.02120v1",
      "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.02120v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.02120v1",
      "pages": 9,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "SkeleWAM: Skeleton World-Action Modeling for Efficient Robotic Manipulation",
      "sourceVersion": "2610.02120v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.191572+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.02120v1"
    },
    {
      "id": "arxiv-2610.02110",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.02110v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.02110v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.02110v1",
      "sha256": "3c2c8f767dcf50db211313387be31c614832d420aada78bc37c217830a156f41",
      "bytes": 5019763,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:32:42.883143+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.02110v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.02110v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.02110v1",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "GlassGuard: Verified Glass Plane Mapping for Robot Navigation",
      "sourceVersion": "2610.02110v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.197103+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.02110v1"
    },
    {
      "id": "arxiv-2610.02089",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.02089v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.02089v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.02089v1",
      "sha256": "d867b8a22da206cc4b9102c5246098fac73c9da6523d8ecd45eb34843b804693",
      "bytes": 10474149,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:32:47.688435+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.02089v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.02089v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.02089v1",
      "pages": 9,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "HumanoidToolBench: Benchmarking Humanoid Tool Use from Selection to Mobile Execution",
      "sourceVersion": "2610.02089v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.208308+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.02089v1"
    },
    {
      "id": "arxiv-2610.02054",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.02054v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.02054v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.02054v1",
      "sha256": "d1c9eb01621c36f3f72a51f7cb1fb5cb457e7f24ba2b322ba4208097a09b1106",
      "bytes": 21229870,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:32:52.224224+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.02054v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.02054v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.02054v1",
      "pages": 29,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "UniWAM: Unified World-Action Model",
      "sourceVersion": "2610.02054v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.231578+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.02054v1"
    },
    {
      "id": "arxiv-2610.01985",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01985v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01985v1",
      "sha256": "909222aeff546168d34f2c0c8cd31cfdb1355d694b89c1195d220063b05080e3",
      "bytes": 4851330,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:32:54.755408+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01985v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01985v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01985v1",
      "pages": 20,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "H-SPAR: Hydrodynamic-aware Simulation for Particle Transport and Autonomous Robots",
      "sourceVersion": "2610.01985v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.237418+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01985v1"
    },
    {
      "id": "arxiv-2610.01959",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01959v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01959v1",
      "sha256": "4d06a9baf70c6ca2b252f810891fb628d20d68f82ddf54ce36a5aefefd8c7b07",
      "bytes": 6682937,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:32:59.179894+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01959v1",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01959v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01959v1",
      "pages": 27,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Training-Free Diffusion Planning with Analytical Local Scores",
      "sourceVersion": "2610.01959v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.243730+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01959v1"
    },
    {
      "id": "arxiv-2610.01943",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01943v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01943v1",
      "sha256": "2c4e10375711555a7555c5cfcf256d8387c418d0ffe899756438e3dbdd868b7f",
      "bytes": 3739119,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:33:56.057086+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01943v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01943v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01943v1",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "TouchTherm: Building Multimodal Digital Twins of Objects for Tactile and Thermal Rendering",
      "sourceVersion": "2610.01943v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.250186+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01943v1"
    },
    {
      "id": "arxiv-2610.01910",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01910v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01910v1",
      "sha256": "033aa88c33f537f886e8def34961e834a1acd8196a95e09d0827f296add06970",
      "bytes": 10416851,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:00.386673+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01910v1",
      "license": "http://creativecommons.org/licenses/by-sa/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01910v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01910v1",
      "pages": 16,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Robot Learning on Discrete Surfaces: Theory and Applications",
      "sourceVersion": "2610.01910v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.259371+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01910v1"
    },
    {
      "id": "arxiv-2610.01906",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01906v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01906v1",
      "sha256": "3430d9e4f33e3e99a2323da515f4e02ea4888626730fef9fee836f2145679c52",
      "bytes": 44802818,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:00.558828+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01906v1",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01906v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01906v1",
      "pages": 23,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Towards Physical Underwater Robotic Assistance for Scuba Diver Movement in Confined Spaces",
      "sourceVersion": "2610.01906v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.316708+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01906v1"
    },
    {
      "id": "arxiv-2610.01863",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01863v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01863v1",
      "sha256": "b2e47d97a85159221186b3af0980b5f180e961f2fa406d676da817ba452e289d",
      "bytes": 45541214,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:05.747558+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01863v1",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01863v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01863v1",
      "pages": 26,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "LiteReality-Agent: An Agentic System for Interactable 3D Indoor Scene Reconstruction",
      "sourceVersion": "2610.01863v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.365496+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01863v1"
    },
    {
      "id": "arxiv-2610.01856",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01856v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01856v1",
      "sha256": "ebdddf3a7aa1b797383a056d45bf58477bf7678802f1abb6577aee97ab8178f0",
      "bytes": 1273702,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:05.712247+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01856v1",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01856v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01856v1",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "ChunkVLA-AM: Parallel Action Chunking for Vision-Language-Action Robot Control in Additive Manufacturing",
      "sourceVersion": "2610.01856v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.369789+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01856v1"
    },
    {
      "id": "arxiv-2610.01849",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01849v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01849v1",
      "sha256": "31732324fd23a050541c610126d28822b6806a940a32701f3792fb74a867c082",
      "bytes": 16279287,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:05.743499+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01849v1",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01849v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01849v1",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "FlashDexRetarget: Accelerating Dexterous Manipulation Data Generation through Multi-Motion Retargeting",
      "sourceVersion": "2610.01849v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.382704+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01849v1"
    },
    {
      "id": "arxiv-2610.01794",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01794v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01794v1",
      "sha256": "7ef7e2724a418bd6304900be351dc2009b5255244c6fd2454ab0f207a8ddff79",
      "bytes": 1745822,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:12.400951+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01794v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01794v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01794v1",
      "pages": 7,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Continuous Conditioning of VLAs with Augmenting EMG and Visual Task Descriptors",
      "sourceVersion": "2610.01794v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.386452+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01794v1"
    },
    {
      "id": "arxiv-2610.01744",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01744v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01744v1",
      "sha256": "492c6bd17f5829458b43b191e9e5c10e14f8ecc62026352a1e6258442426b510",
      "bytes": 1643526,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:12.420884+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01744v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01744v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01744v1",
      "pages": 12,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "3DROID: A Renderable 3D Gaussian Dataset with Measured Per-Scene Reliability",
      "sourceVersion": "2610.01744v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.388521+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01744v1"
    },
    {
      "id": "arxiv-2610.01742",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01742v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01742v1",
      "sha256": "b9c49936d9545f1f106c2b36b2d7e0190018a429fcf9e7c94d64a2a5de89e298",
      "bytes": 6670644,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:12.450379+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01742v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01742v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01742v1",
      "pages": 22,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "World Motion Models: Flexible Sequence Modeling of SE(3) Trajectories",
      "sourceVersion": "2610.01742v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.394223+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01742v1"
    },
    {
      "id": "arxiv-2610.01726",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01726v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01726v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01726v1",
      "sha256": "277143ac5001b83db468384be375aeb31b1aaf2f1f78a04d2cb684d47b773eed",
      "bytes": 17514406,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:22.317227+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01726v1",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01726v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01726v1",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Query-Conditioned Articulation Estimation from a Single Image",
      "sourceVersion": "2610.01726v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.410705+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01726v1"
    },
    {
      "id": "arxiv-2610.01698",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01698v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01698v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01698v1",
      "sha256": "07746732e5e30a92a3679d2ebde7382800ee493cb36bd9d43c066db598b980c8",
      "bytes": 5183115,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:22.017350+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01698v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01698v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01698v1",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "ActiveWAM: Evidence-Aware Active Vision for World-Action Models",
      "sourceVersion": "2610.01698v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.415343+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01698v1"
    },
    {
      "id": "arxiv-2610.01682",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01682v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01682v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01682v1",
      "sha256": "ed572fc24af8c8fb22b182d7d80f4cf1f5fa5782fd40af3d276e0c975ad63a7c",
      "bytes": 790812,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:26.131768+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01682v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01682v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01682v1",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Beyond Leaderboard Scores: A Deployment-Focused Protocol for Interpretable Tracking Evaluation in Pedestrian-Centric Environments",
      "sourceVersion": "2610.01682v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.418071+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01682v1"
    },
    {
      "id": "arxiv-2610.01644",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01644v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01644v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01644v1",
      "sha256": "222df7708016ff8dc1162b8afc89960b4e8221bd2712309037aefea8493228bd",
      "bytes": 2081277,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:31.794993+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01644v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01644v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01644v1",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "SonarVoxNet: Diver Detection in 3D Bounding Box using 3D Sonar",
      "sourceVersion": "2610.01644v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.420449+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01644v1"
    },
    {
      "id": "arxiv-2610.01612",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01612v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01612v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01612v1",
      "sha256": "50e765a2e16b9f5bffddf0d11f8f4254d9237fa039b99ccaef4b20de0a2886fc",
      "bytes": 5996657,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:36.694107+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01612v1",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01612v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01612v1",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "ReCo: Response-Consistent Locomotion with Policy-Aware MPC for Legged Manipulation",
      "sourceVersion": "2610.01612v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.425421+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01612v1"
    },
    {
      "id": "arxiv-2610.01559",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01559v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01559v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01559v1",
      "sha256": "5537afade60a1e45278ff5285e61a29ba65650a754e165be7d807fba52ed31c4",
      "bytes": 3776669,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:36.563001+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01559v1",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01559v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01559v1",
      "pages": 6,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Completion Aware Guidance for World Action Models",
      "sourceVersion": "2610.01559v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.429183+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01559v1"
    },
    {
      "id": "arxiv-2610.01505",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01505v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01505v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01505v1",
      "sha256": "1d62007ac08414a9e3948ca7e9f02a253c3423c1bb8f109db84c420348f0d268",
      "bytes": 550954,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:47.004170+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01505v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01505v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01505v1",
      "pages": 5,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "OpenSpace Lab Solution to the IROS 2026 Indoor Exploration Competition",
      "sourceVersion": "2610.01505v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.430756+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01505v1"
    },
    {
      "id": "arxiv-2610.01477",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01477v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01477v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01477v1",
      "sha256": "d84ee99466a8257fe6fb3ed1cc4378bf936c0b001681b8ceedb717ffc50d998e",
      "bytes": 19956185,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:47.539541+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01477v1",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01477v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01477v1",
      "pages": 36,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "ALFRED: Requirement-driven development of an open-source mobile manipulator for long-term plant monitoring",
      "sourceVersion": "2610.01477v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.445901+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01477v1"
    },
    {
      "id": "arxiv-2610.01397",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01397v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01397v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01397v1",
      "sha256": "85a0a26ac6bf5a2a1af44a4e07ee9e6c89c771186684cd587b19c50bde3834ea",
      "bytes": 3185906,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:51.365283+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01397v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01397v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01397v1",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Continue, Abort, or Fall: Viability-Aware Policy Selection (VAPS) for Safe Humanoid Acrobatics",
      "sourceVersion": "2610.01397v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.449189+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01397v1"
    },
    {
      "id": "arxiv-2610.01351",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01351v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01351v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01351v1",
      "sha256": "162190985a1d39616e85e08077d75c671a4c66350c7fd97e8f9a2ca7def13272",
      "bytes": 612365,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:56.910874+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01351v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01351v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01351v1",
      "pages": 9,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Is Success All You Need? Investigating the Impact of Input Perturbations on VLA Behaviour in Tabletop Manipulation Tasks",
      "sourceVersion": "2610.01351v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.451850+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01351v1"
    },
    {
      "id": "arxiv-2610.01310",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01310v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01310v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01310v1",
      "sha256": "95c943c6928655c9e1a70da8c4ce62ffb94c4142b307f18eeb92b9183f64b70a",
      "bytes": 5126420,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:57.052736+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01310v1",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01310v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01310v1",
      "pages": 15,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Ex vivo breach detection using electrical conductivity during robotic pedicle drilling in the spine",
      "sourceVersion": "2610.01310v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.456365+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01310v1"
    },
    {
      "id": "arxiv-2610.01301",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01301v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01301v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01301v1",
      "sha256": "0f3e9555814bee2c4d9b49034f191237796c26b4225d720d535a1dd6631d27a9",
      "bytes": 10164685,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:35:05.708860+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01301v1",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01301v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01301v1",
      "pages": 21,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Continual Learning for 6-DoF Grasp Synthesis via Experience and Demonstrations",
      "sourceVersion": "2610.01301v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.464050+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01301v1"
    },
    {
      "id": "arxiv-2610.01288",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01288v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01288v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01288v1",
      "sha256": "75d4cc45c9414abbba86645a3e157aea9c22e5c0275eb0b906ca20ff5f98b70b",
      "bytes": 2925520,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:35:05.553007+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01288v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01288v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01288v1",
      "pages": 12,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Interaction-Stiffness-Guided Basis Allocation in Dynamic Movement Primitives for Efficient Skill Transfer",
      "sourceVersion": "2610.01288v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.467403+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01288v1"
    },
    {
      "id": "arxiv-2610.01260",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01260v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01260v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01260v1",
      "sha256": "91068a3909fad60606b289d8e3432d205e0dc13440c32010f4882c2f923c0666",
      "bytes": 8146975,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:35:11.362912+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01260v1",
      "license": "http://creativecommons.org/licenses/by-sa/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01260v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01260v1",
      "pages": 18,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "PROMO: Preference-conditioned Multi-Objective Reinforcement Learning for Quadrupedal Robots",
      "sourceVersion": "2610.01260v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.475788+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01260v1"
    },
    {
      "id": "arxiv-2610.01258",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01258v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01258v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01258v1",
      "sha256": "dc41ef930d411340bf530499d13732c53829aa55262a7f463b67356f61c38f0b",
      "bytes": 5380356,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:35:17.804016+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01258v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01258v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01258v1",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "ColoACT: Multi-Cue Action Chunking for Smooth Autonomous Colon Navigation on a Self-Propelled Endoscopic Robot",
      "sourceVersion": "2610.01258v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.480962+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01258v1"
    },
    {
      "id": "arxiv-2610.01224",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01224v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01224v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01224v1",
      "sha256": "3aa8ed58541abbc8a6bd56f12fa4b8bbe1ce00e3dab4c8c53cfe9e60c30edfa7",
      "bytes": 1823996,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:35:17.752495+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01224v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01224v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01224v1",
      "pages": 21,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Supervise What Decides Success: Criterion-Aligned Auxiliary Losses for Latent World-Model Planning",
      "sourceVersion": "2610.01224v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.484202+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01224v1"
    },
    {
      "id": "arxiv-2610.01219",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01219v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01219v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01219v1",
      "sha256": "67bb3ec388afa7ec9dd899f5245f38a7383ae7128e7e4eb9f58f470649bad7d8",
      "bytes": 5722978,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:35:24.159287+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01219v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01219v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01219v1",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "EIDA: Execution-Interface Dynamics Adaptation for Real-to-Sim-to-Real Robot Navigation",
      "sourceVersion": "2610.01219v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.489739+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01219v1"
    },
    {
      "id": "arxiv-2610.01178",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01178v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01178v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01178v1",
      "sha256": "9e97f8d4a2ad86a447748a9dd968b97a18230b42a884c5a68610b6aaeb1e7a64",
      "bytes": 6838410,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:35:34.079063+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01178v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01178v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01178v1",
      "pages": 23,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Recova: Agent-Guided Failure Recovery for Autonomous Robotic Manipulation",
      "sourceVersion": "2610.01178v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.495306+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01178v1"
    },
    {
      "id": "arxiv-2610.01171",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01171v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01171v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01171v1",
      "sha256": "2c5f073c7d74083ec3f9275d2a2740c56fa977f03a942473912a2511ef5b0172",
      "bytes": 2995207,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:35:33.964594+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01171v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01171v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01171v1",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Experience-Based Feasibility-Aware Generative Adversarial Imitation from Observation under Embodiment Mismatch",
      "sourceVersion": "2610.01171v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.498884+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01171v1"
    },
    {
      "id": "arxiv-2610.01162",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01162v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01162v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01162v1",
      "sha256": "f2d63c19df085c547f9f4609ca4b09e7f3651f0cca749e07c2f1b26ea702cc06",
      "bytes": 6754311,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:35:41.240701+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01162v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01162v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01162v1",
      "pages": 21,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "PhysicsLENS: Diagnosing Physical Property Blindness in Video Generation Models",
      "sourceVersion": "2610.01162v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.505448+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01162v1"
    },
    {
      "id": "arxiv-2610.01105",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01105v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01105v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01105v1",
      "sha256": "f29179f46cccb463f01f4956158799b168dc7a25d9d1491ac4b574c114e9ef87",
      "bytes": 4379866,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:35:45.727933+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01105v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01105v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01105v1",
      "pages": 4,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Extreme Length Generalization in a Compact Recurrent Architecture for One-Shot Exploration",
      "sourceVersion": "2610.01105v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.509553+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01105v1"
    },
    {
      "id": "arxiv-2610.01102",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01102v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01102v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01102v1",
      "sha256": "ef6791faecbb1ef9eaa8a608f9071c825cbf28e06d37cf11f5f13778b9e1695d",
      "bytes": 12049652,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:35:45.878812+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01102v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01102v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01102v1",
      "pages": 22,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "MASkillBlender: Decentralized Whole-Body Coordination for Multi-Humanoid Loco-Manipulation via Skill Blending",
      "sourceVersion": "2610.01102v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.519898+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01102v1"
    },
    {
      "id": "arxiv-2610.01083",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01083v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01083v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01083v1",
      "sha256": "ffb75d2e97fbbb22bee133a75b27403e4f4d2951f6029bbeb3db904f4a7c1307",
      "bytes": 8440307,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:35:54.502348+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01083v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01083v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01083v1",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "WBAG: A Whole-Body and Attached-Geometry Safety Framework for Vision-Language-Action Manipulation",
      "sourceVersion": "2610.01083v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.527004+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01083v1"
    },
    {
      "id": "arxiv-2610.01072",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01072v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01072v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01072v1",
      "sha256": "333a51f18e859636881d33e45df987399e95f7b054b05edb1440eb55e9887c67",
      "bytes": 18873096,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:35:54.754576+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01072v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01072v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01072v1",
      "pages": 58,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "quARtet Marker: A 3D-Printable Multi-Tag Fiducial for Robust Near-Frontal Pose Estimation",
      "sourceVersion": "2610.01072v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.542382+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01072v1"
    },
    {
      "id": "arxiv-2610.01019",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01019v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01019v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01019v1",
      "sha256": "c6d35ba6d0b05f199ecc50bcb4899190e9e9ee09c21237b1f7a96d148064bc87",
      "bytes": 33680170,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:36:00.390254+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01019v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01019v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01019v1",
      "pages": 32,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "FutureWorlds: Learning Robotic World Models from Alternative Futures",
      "sourceVersion": "2610.01019v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.574996+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01019v1"
    },
    {
      "id": "arxiv-2610.01004",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.01004v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.01004v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.01004v1",
      "sha256": "f796a8d4eecf2999a452eb1f23e81be9854a498dd1fa58763c8c346d9df23ef5",
      "bytes": 9377286,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:36:04.963300+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.01004v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.01004v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.01004v1",
      "pages": 10,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "The Effect of Gait Stability Based on Two Types of Impact Strategies for Two-Link Walking and Brachiating Robots",
      "sourceVersion": "2610.01004v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.583980+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.01004v1"
    },
    {
      "id": "arxiv-2610.00982",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00982v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00982v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00982v1",
      "sha256": "31070beb3c4ab4ff1fa166c04b920b5c4816ef220b88729147b9405e15be3346",
      "bytes": 8606466,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:36:11.356301+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00982v1",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00982v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00982v1",
      "pages": 27,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Divide-and-Remember: Recursive Action-Relevant Memory for Long-Horizon VLA Policies",
      "sourceVersion": "2610.00982v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.591199+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00982v1"
    },
    {
      "id": "arxiv-2610.00981",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00981v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00981v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00981",
      "sha256": "9e15201052d0fc948b2497c7643afe2406831f3b825b8114327c5c788427b6bb",
      "bytes": 5040404,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:43:03.021296+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00981",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00981",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00981",
      "pages": 24,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "NarrativeFlow: Flow-Based Vision-Language-Action Model Using Robot Velocity Fields",
      "sourceVersion": "2610.00981v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.563264+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00981"
    },
    {
      "id": "arxiv-2610.00921",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00921v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00921v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00921",
      "sha256": "846471c39c478d54b094e6b616e1efbde96d0a596b0b881198676fda2002d677",
      "bytes": 572890,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:43:02.888294+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00921",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00921",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00921",
      "pages": 20,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "In CEM, a World Model Is Also a Proposal Mechanism",
      "sourceVersion": "2610.00921v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.564728+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00921"
    },
    {
      "id": "arxiv-2610.00913",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00913v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00913v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00913",
      "sha256": "99bd6e54b9370ad65d298e20902c8736c506ad9c24557da4726871d41e37d496",
      "bytes": 8904353,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:43:03.116411+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00913",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00913",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00913",
      "pages": 21,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "eRLT: Efficient VLA Reinforcement Learning via Action-Relevant Token Routing",
      "sourceVersion": "2610.00913v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.571670+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00913"
    },
    {
      "id": "arxiv-2610.00904",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00904v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00904v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00904",
      "sha256": "80b8b57838ab9dafadeab2ec237fec3c9fc9597d0cd83afe080ee1af0b4c3493",
      "bytes": 1609601,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:43:14.760453+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00904",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00904",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00904",
      "pages": 17,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Screw Attention: Rigid-Body Algebra Inside a Transformer",
      "sourceVersion": "2610.00904v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.574212+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00904"
    },
    {
      "id": "arxiv-2610.00899",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00899v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00899v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00899",
      "sha256": "7d32b2fe30393f482558eb50947f5764c554703fa7012d91821ba92e7d6627ef",
      "bytes": 5374014,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:33:10.604532+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00899",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00899",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00899",
      "pages": 10,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "TOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action Models",
      "sourceVersion": "2610.00899v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.140170+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00899"
    },
    {
      "id": "arxiv-2610.00897",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00897v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00897v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00897",
      "sha256": "f3ce897e305834e7e2343caac8438cb3e4e3e7589ac3a9d2a53761ade95076c0",
      "bytes": 5265792,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:43:14.872588+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00897",
      "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00897",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00897",
      "pages": 10,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Real-Time Human-Adaptive Task Allocation for Multi-Human Multi-Robot Supervision",
      "sourceVersion": "2610.00897v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.579733+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00897"
    },
    {
      "id": "arxiv-2610.00878",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00878v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00878v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00878",
      "sha256": "96d03780cfb2ae8e92a1e3aa4456520845d5d17ab48fcce1ed469e403c8b4706",
      "bytes": 14192716,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:43:15.091145+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00878",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00878",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00878",
      "pages": 9,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "UniTrackPLA: Unified Panorama-Language-Action Model for Instruction-Guided Navigation and Dynamic Person Tracking",
      "sourceVersion": "2610.00878v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.592815+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00878"
    },
    {
      "id": "arxiv-2610.00864",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00864v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00864v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00864",
      "sha256": "8b4929f164860d768f2960625bb5a3a9b2b0ae7e577fa0e0a94106628f14f84c",
      "bytes": 22731291,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:43:24.514221+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00864",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00864",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00864",
      "pages": 18,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models",
      "sourceVersion": "2610.00864v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.611285+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00864"
    },
    {
      "id": "arxiv-2610.00854",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00854v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00854v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00854",
      "sha256": "b824475f46cfe7a1e9a67263286e751e2309101294a5e8c95425c5888f80fe77",
      "bytes": 21941418,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:43:24.559531+00:00",
      "publicationDate": "2026/10/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00854",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00854",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00854",
      "pages": 40,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Are Frontier VLM Agents Ready to Be Robot Generalists? An Empirical Study with the Embodied Agent Arena",
      "sourceVersion": "2610.00854v1",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.633904+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00854"
    },
    {
      "id": "arxiv-2610.00823",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00823v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00823v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00823",
      "sha256": "c178065b037923e2cebc7d02c2ae4b98fcbbef077a488fd2b2d3e922f9d5b6b0",
      "bytes": 4810163,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:43:30.163901+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00823",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00823",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00823",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Reactive Humanoid Multi-Contact Using Learned Stability Models",
      "sourceVersion": "2610.00823v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.638701+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00823"
    },
    {
      "id": "arxiv-2610.00822",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00822v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00822v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00822",
      "sha256": "a16b686f990ad1e024a8af24884931d0e1021e3f04e5ef32f144923264391fda",
      "bytes": 1144846,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:43:35.099317+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00822",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00822",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00822",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "TRACE: Privacy-Preserving Next-Best-View Selection over Distributed 3D Gaussian-Splat Maps",
      "sourceVersion": "2610.00822v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.642586+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00822"
    },
    {
      "id": "arxiv-2610.00801",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00801v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00801v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00801",
      "sha256": "1a1b71465841402967dfd31707375269b9c185a6a821fbccac3d10ed86934f3a",
      "bytes": 9099114,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:43:35.349937+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00801",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00801",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00801",
      "pages": 29,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "ECoMEM: Explicit Concept Memory for Memory-Dependent Robot Control",
      "sourceVersion": "2610.00801v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.652374+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00801"
    },
    {
      "id": "arxiv-2610.00781",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00781v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00781v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00781",
      "sha256": "d1c4396096690834fbfc144e0e64ee870efd2de76ed28f6e11f471bac2271977",
      "bytes": 5584834,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:43:47.787358+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00781",
      "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00781",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00781",
      "pages": 9,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "DITTO-X: Forward and Reverse Teleoperation for Dexterous Manipulation and Human Intervention",
      "sourceVersion": "2610.00781v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.659351+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00781"
    },
    {
      "id": "arxiv-2610.00731",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00731v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00731v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00731",
      "sha256": "392146b25295eb4489f0c3a6b922d8e576029442921eb014e489a7f6a5bb025e",
      "bytes": 3191185,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:43:47.771774+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00731",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00731",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00731",
      "pages": 20,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Measuring Asset and Scene Reconstruction Effects in Real-to-Sim Robot Evaluation",
      "sourceVersion": "2610.00731v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.662798+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00731"
    },
    {
      "id": "arxiv-2610.00729",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00729v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00729v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00729",
      "sha256": "90eee95f553908b718ce7662a436a4b991a3793a77802119df3501805e00e131",
      "bytes": 2916928,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:43:52.379876+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00729",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00729",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00729",
      "pages": 9,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Reward as Observation: Learning Reward-Based Policies for Rapid Adaptation",
      "sourceVersion": "2610.00729v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.666183+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00729"
    },
    {
      "id": "arxiv-2610.00727",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00727v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00727v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00727",
      "sha256": "1ea7f2fb228bc0bf9412956b4af0dd51334cab1925308e528474e7b141467429",
      "bytes": 585069,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:43:57.458735+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00727",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00727",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00727",
      "pages": 9,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "CF-JEPA: Improving Robustness of JEPA World Models via Controllability Factorization",
      "sourceVersion": "2610.00727v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.667784+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00727"
    },
    {
      "id": "arxiv-2610.00718",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00718v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00718v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00718",
      "sha256": "aaa282158ac3d1baeefcf3616f562b5c9865fa61876280a0e2ae96fbd7835ce1",
      "bytes": 22118302,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:43:58.036533+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00718",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00718",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00718",
      "pages": 4,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Toward Humanoid Robots in Construction: A Teleoperation Feasibility Study",
      "sourceVersion": "2610.00718v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.685419+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00718"
    },
    {
      "id": "arxiv-2610.00638",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00638v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00638v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00638",
      "sha256": "c1ef04fd0a97fc2e91cd8b15a00b3ab452d9e2a036ce645b56bb35e93c4ed112",
      "bytes": 4839863,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:44:08.516208+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00638",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00638",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00638",
      "pages": 21,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "TacDyn-WAM: Learning Implicit Tactile Dynamics in a Heterogeneous Visuo-Tactile World Action Model",
      "sourceVersion": "2610.00638v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.690647+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00638"
    },
    {
      "id": "arxiv-2610.00604",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00604v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00604v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00604",
      "sha256": "a6eaf2e89521914bad5b86f1f05ea1caec20dd0690511a21730fe6a7a3f19b67",
      "bytes": 30283158,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:44:09.219187+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00604",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00604",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00604",
      "pages": 57,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "MIKASA-Robo-VLA: Benchmarking Memory in VLA Models for Long-Horizon Manipulation",
      "sourceVersion": "2610.00604v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.719406+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00604"
    },
    {
      "id": "arxiv-2610.00601",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00601v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00601v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00601",
      "sha256": "19a733df1a80ccf86a5b9beeacdd41c33ea32e6b4686f1892c4abb7182ae04df",
      "bytes": 2621149,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:44:11.840669+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00601",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00601",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00601",
      "pages": 10,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "When Reasoning Helps Action: Monitoring and Steering Chain-of-Thought in Vision-Language-Action Policies",
      "sourceVersion": "2610.00601v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.723969+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00601"
    },
    {
      "id": "arxiv-2610.00575",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00575v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00575v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00575",
      "sha256": "beff8246d721bffc0f97751dc91735f6f80e0f9ca2fcf2588187391292fd0e2b",
      "bytes": 5065985,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:44:16.490527+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00575",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00575",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00575",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Token-World: World Modeling in Vision-Language Model Token Space for Robot Manipulation",
      "sourceVersion": "2610.00575v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.728560+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00575"
    },
    {
      "id": "arxiv-2610.00542",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00542v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00542v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00542",
      "sha256": "508b48f9d147d5f12c9dc7551df39add4e04b33d105c5938af30b5dedb7f6453",
      "bytes": 1746195,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:44:21.999371+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00542",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00542",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00542",
      "pages": 9,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Does Continual Imitation Learning Remain Grounded? A Language-Perturbed Benchmark for Robotic Task Retention",
      "sourceVersion": "2610.00542v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.730720+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00542"
    },
    {
      "id": "arxiv-2610.00524",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00524v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00524v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00524",
      "sha256": "75c9d2e3c4114da3eabfcf4745ed96375d8586a16425bdc0f777ea81385be618",
      "bytes": 13942404,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:44:22.189792+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00524",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00524",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00524",
      "pages": 26,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Same Scene, Different Task: Skill Alignment for Compositional Generalization in VLAs",
      "sourceVersion": "2610.00524v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.741011+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00524"
    },
    {
      "id": "arxiv-2610.00487",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00487v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00487v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00487",
      "sha256": "28d7c3778489a86cc7e23cfe0cc75b2cbd8269b0684183cf747d15ea8669dd90",
      "bytes": 8615629,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:44:29.542916+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00487",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00487",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00487",
      "pages": 13,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "ScaffoldM3C: A Multimodal Sequential Monte Carlo Framework for Generative Stable Construction Planning",
      "sourceVersion": "2610.00487v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.749043+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00487"
    },
    {
      "id": "arxiv-2610.00438",
      "originalSourceUrl": "https://arxiv.org/pdf/2610.00438v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2610.00438v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2610.00438",
      "sha256": "6d2e48b284c9d2d6a21882239cb6dcec5b493744c1bac0bcd2681008849fbc76",
      "bytes": 39808001,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:45:01.091998+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2610.00438",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2610.00438",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2610.00438",
      "pages": 15,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Towards a General Humanoid Loco-Manipulation Model via Egocentric Whole-Body Human Data Pretraining",
      "sourceVersion": "2610.00438v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.824771+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2610.00438"
    },
    {
      "id": "arxiv-2609.40353",
      "originalSourceUrl": "https://arxiv.org/pdf/2609.40353v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2609.40353v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2609.40353",
      "sha256": "97d311f41e51e9e96c1176176faad8f4ac518691794b3581a2a5703e121cb289",
      "bytes": 3386510,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:44:34.560316+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2609.40353",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2609.40353",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2609.40353",
      "pages": 24,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "AssemblyWorld: Rethinking 3D Assembly with General-Purpose Agents",
      "sourceVersion": "2609.40353v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.753031+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2609.40353"
    },
    {
      "id": "arxiv-2609.40341",
      "originalSourceUrl": "https://arxiv.org/pdf/2609.40341v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2609.40341v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2609.40341",
      "sha256": "09789e8fe4711a3c3fdd578eebd8e681ca91a9e36d525346d7dd440de3fdfaab",
      "bytes": 7262487,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:44:34.674497+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2609.40341",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2609.40341",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2609.40341",
      "pages": 18,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Ego4WAM: What Matters When Scaling Egocentric Human Data for Robot Learning?",
      "sourceVersion": "2609.40341v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.760769+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2609.40341"
    },
    {
      "id": "arxiv-2609.40306",
      "originalSourceUrl": "https://arxiv.org/pdf/2609.40306v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2609.40306v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2609.40306",
      "sha256": "e07c7fd79a2e6690f64cbc07f501894bc96d07c9bc091a735a7ef403572ddd1d",
      "bytes": 7704124,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:44:40.225343+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2609.40306",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2609.40306",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2609.40306",
      "pages": 37,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents",
      "sourceVersion": "2609.40306v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.768148+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2609.40306"
    },
    {
      "id": "arxiv-2609.40297",
      "originalSourceUrl": "https://arxiv.org/pdf/2609.40297v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2609.40297v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2609.40297",
      "sha256": "6c77b23296c0777f5a6eb430ef3e790a5972def4c3e4c39ab4891d3e7aa9a9a5",
      "bytes": 1085579,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:44:46.862218+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2609.40297",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2609.40297",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2609.40297",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "GPU-Accelerated Path-Dependent Marginal Information Gain for Autonomous Exploration",
      "sourceVersion": "2609.40297v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.770682+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2609.40297"
    },
    {
      "id": "arxiv-2609.40245",
      "originalSourceUrl": "https://arxiv.org/pdf/2609.40245v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2609.40245v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2609.40245",
      "sha256": "9d87aa14858069890ac9bfcb61bfbe9884777d11f70eb7900fffe9e5adf650fc",
      "bytes": 3859822,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:44:50.774302+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2609.40245",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2609.40245",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked_with_abstract_conflict",
      "metadataSourceUrl": "https://arxiv.org/abs/2609.40245",
      "pages": 26,
      "sourceIdentityStatus": "title_and_arxiv_id_match_abstract_conflict",
      "sourceTitle": "STARS: From Spatiotemporal Dynamics to Social Representations in Human-Robot Interaction",
      "sourceVersion": "2609.40245v2",
      "sourceVersionDate": "2026/10/01",
      "archiveValidationStatus": "file_validated_metadata_conflict",
      "archiveValidatedAt": "2026-10-04T13:45:15.774332+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2609.40245",
      "metadataConflict": {
        "status": "confirmed_upstream_abstract_inconsistency",
        "affectedFields": [
          "arXiv landing-page abstract",
          "arXiv citation_abstract",
          "collector abstractOriginal"
        ],
        "finding": "Current unversioned and versioned v2 arXiv landing metadata use the STARS title, but their abstract describes introducing the SocialNav-SUB VQA benchmark. The versioned v2 PDF instead presents STARS, a self-supervised spatiotemporal graph autoencoder with linear-probe evaluation. Its title, authors, arXiv ID, and version match the archive. This is an upstream metadata/PDF abstract inconsistency, not a mismatched local PDF. The cause of the upstream inconsistency is not established.",
        "currentLandingUrl": "https://arxiv.org/abs/2609.40245",
        "currentVersionedLandingUrl": "https://arxiv.org/abs/2609.40245v2",
        "versionedPdfUrl": "https://arxiv.org/pdf/2609.40245v2",
        "currentVersionedPdfSha256": "9d87aa14858069890ac9bfcb61bfbe9884777d11f70eb7900fffe9e5adf650fc",
        "versionedPdfMatchesArchivedBytes": true,
        "checkedAt": "2026-10-04T13:54:03.645251+00:00"
      }
    },
    {
      "id": "arxiv-2609.40244",
      "originalSourceUrl": "https://arxiv.org/pdf/2609.40244v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2609.40244v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2609.40244",
      "sha256": "4517b0d05796f974a8056133a25059a891b65f1d9bf244932c45195a37175358",
      "bytes": 3233792,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:44:50.641305+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2609.40244",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2609.40244",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2609.40244",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "StreamRig: Exploiting Intra-Rig Geometry for Streaming Multi-Camera Odometry",
      "sourceVersion": "2609.40244v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.778011+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2609.40244"
    },
    {
      "id": "arxiv-2609.40208",
      "originalSourceUrl": "https://arxiv.org/pdf/2609.40208v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2609.40208v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2609.40208",
      "sha256": "34d760ade1448af94a2e1f5dee7a285f94ca458fc30a38a9f8fa314874733f4d",
      "bytes": 4137949,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:45:00.353255+00:00",
      "publicationDate": "2026/09/30",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2609.40208",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2609.40208",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2609.40208",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Centralized Multi-UAV Exploration and 3D Reconstruction Using Single-UAV Planners",
      "sourceVersion": "2609.40208v1",
      "sourceVersionDate": "2026/09/30",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.830323+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2609.40208"
    },
    {
      "id": "arxiv-2609.34018",
      "originalSourceUrl": "https://arxiv.org/pdf/2609.34018v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2609.34018v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2609.34018",
      "sha256": "de94b28080ee3f4a10971a551b7cee14ea976b7c0066644663b523c6c7b25a2f",
      "bytes": 3405417,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:33:10.712064+00:00",
      "publicationDate": "2026/09/27",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2609.34018",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2609.34018",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2609.34018",
      "pages": 9,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Estimate, Don't Imitate: Reusing Differentiable State-Based Policies for Visuomotor Control",
      "sourceVersion": "2609.34018v1",
      "sourceVersionDate": "2026/09/27",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.595046+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2609.34018"
    },
    {
      "id": "arxiv-2609.28959",
      "originalSourceUrl": "https://arxiv.org/pdf/2609.28959v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2609.28959v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2609.28959",
      "sha256": "d08d4cfbcd719d59aadf34325c7763c9b8c6b029e8c85435a5f652705c798426",
      "bytes": 5222638,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:33:10.696557+00:00",
      "publicationDate": "2026/09/24",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2609.28959",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2609.28959",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2609.28959",
      "pages": 18,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "TactileStep: Sole Tactile Learning for Regulating Foot-Terrain Interaction in Humanoid Locomotion",
      "sourceVersion": "2609.28959v1",
      "sourceVersionDate": "2026/09/24",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.600053+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2609.28959"
    },
    {
      "id": "arxiv-2609.28660",
      "originalSourceUrl": "https://arxiv.org/pdf/2609.28660v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2609.28660v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2609.28660",
      "sha256": "abaee0b7796a4ab0fd4542b7f8fbbf2378fa1127358026596abfd4ca7d3900da",
      "bytes": 11523336,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:33:22.104666+00:00",
      "publicationDate": "2026/09/23",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2609.28660",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2609.28660",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2609.28660",
      "pages": 24,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Morphometric Imitation: From Morphology and Contact Aware Hand Retargeting to Sim-to-Real Visuomotor Policy",
      "sourceVersion": "2609.28660v2",
      "sourceVersionDate": "2026/09/25",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.609202+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2609.28660"
    },
    {
      "id": "arxiv-2609.28258",
      "originalSourceUrl": "https://arxiv.org/pdf/2609.28258v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2609.28258v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2609.28258",
      "sha256": "574d3c826735bb20fac4fa70aee84e7a8248394f62e75411828b04ddcfcc47c1",
      "bytes": 3383401,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:33:21.870882+00:00",
      "publicationDate": "2026/09/23",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2609.28258",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2609.28258",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2609.28258",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Generalizable Robotic Insertion with World Models",
      "sourceVersion": "2609.28258v1",
      "sourceVersionDate": "2026/09/23",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.613409+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2609.28258"
    },
    {
      "id": "arxiv-2609.24682",
      "originalSourceUrl": "https://arxiv.org/pdf/2609.24682v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2609.24682v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2609.24682",
      "sha256": "3abb895e9911cf97a2a279ec51d0c8282295d5ad7e2e4aa4f7bf0c10289a9c4e",
      "bytes": 5372281,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:33:22.025430+00:00",
      "publicationDate": "2026/09/21",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2609.24682",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2609.24682",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2609.24682",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Think Like a World Model, Act Like a VLA: Distilling World-Model Representations into Compact Robot Policies",
      "sourceVersion": "2609.24682v2",
      "sourceVersionDate": "2026/09/22",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.618573+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2609.24682"
    },
    {
      "id": "arxiv-2609.23968",
      "originalSourceUrl": "https://arxiv.org/pdf/2609.23968v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2609.23968v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2609.23968",
      "sha256": "a4c1f70308b89a38ff4967b5b57b92a5a3cc59b97f76236ed1421b20746ea124",
      "bytes": 17021553,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:33:36.971210+00:00",
      "publicationDate": "2026/09/21",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2609.23968",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2609.23968",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2609.23968",
      "pages": 18,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Opt2VLA: Force-Aware Vision-Language-Action for Contact-Rich Humanoid Whole-Body Manipulation",
      "sourceVersion": "2609.23968v1",
      "sourceVersionDate": "2026/09/21",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.631188+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2609.23968"
    },
    {
      "id": "arxiv-2609.22895",
      "originalSourceUrl": "https://arxiv.org/pdf/2609.22895v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2609.22895v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2609.22895",
      "sha256": "41125aece3618a5f2b9a7843acce5fb33d55450ab2057f482d75fa36551dec9a",
      "bytes": 22594798,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:33:36.891794+00:00",
      "publicationDate": "2026/09/19",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2609.22895",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2609.22895",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2609.22895",
      "pages": 27,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "H-VLA: Hierarchical Vision-Language-Action Model with Key-Action Reasoning and Motion Planning in a Unified Action Space",
      "sourceVersion": "2609.22895v1",
      "sourceVersionDate": "2026/09/19",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.654249+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2609.22895"
    },
    {
      "id": "arxiv-2609.18293",
      "originalSourceUrl": "https://arxiv.org/pdf/2609.18293v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2609.18293v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2609.18293",
      "sha256": "18bb3e61c5fc614c23508a34edbf63b4570153f8d341d67dc5e8d4e280b6b2aa",
      "bytes": 2636149,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:33:36.504993+00:00",
      "publicationDate": "2026/09/16",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2609.18293",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2609.18293",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2609.18293",
      "pages": 9,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Function-Preserving Data Generation for Zero-Shot Real-to-Sim-to-Real Manipulation",
      "sourceVersion": "2609.18293v1",
      "sourceVersionDate": "2026/09/16",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.658006+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2609.18293"
    },
    {
      "id": "arxiv-2609.13053",
      "originalSourceUrl": "https://arxiv.org/pdf/2609.13053v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2609.13053v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2609.13053",
      "sha256": "18662cabd0593a95cde4b859c0a62334d2e139fc0d88895125abc4f003ca1ac5",
      "bytes": 40846917,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:33:48.105129+00:00",
      "publicationDate": "2026/09/11",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2609.13053",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2609.13053",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2609.13053",
      "pages": 36,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Model",
      "sourceVersion": "2609.13053v1",
      "sourceVersionDate": "2026/09/11",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.696411+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2609.13053"
    },
    {
      "id": "arxiv-2603.09030",
      "originalSourceUrl": "https://arxiv.org/pdf/2603.09030v3",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2603.09030v3",
      "finalDownloadUrl": "https://arxiv.org/pdf/2603.09030",
      "sha256": "18c8bfc90fad9fe6cc387f923035c823c7061f40cada1eae134b62638e3d187f",
      "bytes": 11903343,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:33:46.544895+00:00",
      "publicationDate": "2026/03/09",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2603.09030",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2603.09030",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2603.09030",
      "pages": 25,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "PlayWorld: Learning Robot World Models from Autonomous Play",
      "sourceVersion": "2603.09030v3",
      "sourceVersionDate": "2026/04/06",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.708726+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2603.09030"
    },
    {
      "id": "arxiv-2602.06643",
      "originalSourceUrl": "https://arxiv.org/pdf/2602.06643v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2602.06643v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2602.06643",
      "sha256": "7d73380b98fccd23e69206db2ec0d875634396c62fba24ee277b6679fd2f5e45",
      "bytes": 37246617,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:33:51.460287+00:00",
      "publicationDate": "2026/02/06",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2602.06643",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2602.06643",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2602.06643",
      "pages": 15,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations",
      "sourceVersion": "2602.06643v2",
      "sourceVersionDate": "2026/02/12",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.756134+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2602.06643"
    },
    {
      "id": "arxiv-2511.14759",
      "originalSourceUrl": "https://arxiv.org/pdf/2511.14759v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2511.14759v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2511.14759",
      "sha256": "9f4f5a3070ad9549ea7687ea54baa19858820dbcc0834cc805212d68fd6c8cb3",
      "bytes": 25075375,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:36:11.755411+00:00",
      "publicationDate": "2025/11/18",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2511.14759",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2511.14759",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2511.14759",
      "pages": 18,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "$\\pi^{*}_{0.6}$: a VLA That Learns From Experience",
      "sourceVersion": "2511.14759v2",
      "sourceVersionDate": "2025/11/19",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.780675+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2511.14759"
    },
    {
      "id": "arxiv-2506.09985",
      "originalSourceUrl": "https://arxiv.org/pdf/2506.09985v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2506.09985v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2506.09985",
      "sha256": "9cfcfde5fb0d9730637da5b9e7317825c3f3d09e91f3553e22eeba42c74d2226",
      "bytes": 20240380,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:36:16.510702+00:00",
      "publicationDate": "2025/06/11",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2506.09985",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2506.09985",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2506.09985",
      "pages": 48,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning",
      "sourceVersion": "2506.09985v1",
      "sourceVersionDate": "2025/06/11",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.800205+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2506.09985"
    },
    {
      "id": "arxiv-2506.01844",
      "originalSourceUrl": "https://arxiv.org/pdf/2506.01844v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2506.01844v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2506.01844",
      "sha256": "cb1bb9a8f824187fcdc32af8c290214487c524f139a3c2def1c6d97adb1fa40c",
      "bytes": 8921356,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:36:21.628286+00:00",
      "publicationDate": "2025/06/02",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2506.01844",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2506.01844",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2506.01844",
      "pages": 24,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics",
      "sourceVersion": "2506.01844v1",
      "sourceVersionDate": "2025/06/02",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.809190+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2506.01844"
    },
    {
      "id": "arxiv-2504.16054",
      "originalSourceUrl": "https://arxiv.org/pdf/2504.16054v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2504.16054v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2504.16054",
      "sha256": "6a1029fd8ab6944b74cf22f5e5d30e60bc15699d964b2900af799b807a34b64c",
      "bytes": 16213397,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:36:21.915829+00:00",
      "publicationDate": "2025/04/22",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2504.16054",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2504.16054",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2504.16054",
      "pages": 19,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization",
      "sourceVersion": "2504.16054v1",
      "sourceVersionDate": "2025/04/22",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.822284+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2504.16054"
    },
    {
      "id": "arxiv-2503.14734",
      "originalSourceUrl": "https://arxiv.org/pdf/2503.14734v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2503.14734v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2503.14734",
      "sha256": "76e38cf679637b816b16edf7170340883dd09175bf334aeeaed49392777731b9",
      "bytes": 21021950,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:36:32.501619+00:00",
      "publicationDate": "2025/03/18",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2503.14734",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2503.14734",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2503.14734",
      "pages": 36,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "GR00T N1: An Open Foundation Model for Generalist Humanoid Robots",
      "sourceVersion": "2503.14734v2",
      "sourceVersionDate": "2025/03/27",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.840213+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2503.14734"
    },
    {
      "id": "arxiv-2502.19645",
      "originalSourceUrl": "https://arxiv.org/pdf/2502.19645v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2502.19645v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2502.19645",
      "sha256": "b860aa1206b6cfb0ce8be177f961379dd6a133d52cc74ac346636e0f4952a596",
      "bytes": 26994977,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:36:32.739501+00:00",
      "publicationDate": "2025/02/27",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2502.19645",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2502.19645",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2502.19645",
      "pages": 24,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success",
      "sourceVersion": "2502.19645v2",
      "sourceVersionDate": "2025/04/28",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.869880+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2502.19645"
    },
    {
      "id": "arxiv-2502.01143",
      "originalSourceUrl": "https://arxiv.org/pdf/2502.01143v3",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2502.01143v3",
      "finalDownloadUrl": "https://arxiv.org/pdf/2502.01143",
      "sha256": "8ca60229d7e560769ceece6cb5571d8e6f528c6c485f631b7fd5162d503b7db0",
      "bytes": 36214501,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:36:38.854057+00:00",
      "publicationDate": "2025/02/03",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2502.01143",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2502.01143",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2502.01143",
      "pages": 18,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills",
      "sourceVersion": "2502.01143v3",
      "sourceVersionDate": "2025/04/26",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.907377+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2502.01143"
    },
    {
      "id": "arxiv-2501.09747",
      "originalSourceUrl": "https://arxiv.org/pdf/2501.09747v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2501.09747v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2501.09747",
      "sha256": "3739b31f5fecdde371509ff5bb13619979734e894a255a9b264253f4cc53934a",
      "bytes": 7468382,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:36:43.849473+00:00",
      "publicationDate": "2025/01/16",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2501.09747",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2501.09747",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2501.09747",
      "pages": 19,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "FAST: Efficient Action Tokenization for Vision-Language-Action Models",
      "sourceVersion": "2501.09747v1",
      "sourceVersionDate": "2025/01/16",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.918876+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2501.09747"
    },
    {
      "id": "arxiv-2412.04453",
      "originalSourceUrl": "https://arxiv.org/pdf/2412.04453v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2412.04453v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2412.04453",
      "sha256": "e02fcccae8aad56cf33234882de06b97256b76aad86a011171b83db40790bc8c",
      "bytes": 9981598,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:36:43.906816+00:00",
      "publicationDate": "2024/12/05",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2412.04453",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2412.04453",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2412.04453",
      "pages": 17,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "NaVILA: Legged Robot Vision-Language-Action Model for Navigation",
      "sourceVersion": "2412.04453v2",
      "sourceVersionDate": "2025/02/17",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.929360+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2412.04453"
    },
    {
      "id": "arxiv-2410.24164",
      "originalSourceUrl": "https://arxiv.org/pdf/2410.24164v4",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2410.24164v4",
      "finalDownloadUrl": "https://arxiv.org/pdf/2410.24164",
      "sha256": "fbdfba56258bdbd220207ba63410c6c943e43a73e97a7a5a47ca0bc74204f821",
      "bytes": 7893845,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:36:48.490593+00:00",
      "publicationDate": "2024/10/31",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2410.24164",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2410.24164",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2410.24164",
      "pages": 17,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control",
      "sourceVersion": "2410.24164v4",
      "sourceVersionDate": "2026/01/08",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.939304+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2410.24164"
    },
    {
      "id": "arxiv-2410.07864",
      "originalSourceUrl": "https://arxiv.org/pdf/2410.07864v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2410.07864v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2410.07864",
      "sha256": "fabfa885b63f2d68b8e7868549563c346d4323a596d24ee3e43d0a62b4ef9667",
      "bytes": 9699239,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:36:55.960932+00:00",
      "publicationDate": "2024/10/10",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2410.07864",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2410.07864",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2410.07864",
      "pages": 28,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation",
      "sourceVersion": "2410.07864v2",
      "sourceVersionDate": "2025/03/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.948062+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2410.07864"
    },
    {
      "id": "arxiv-2406.10454",
      "originalSourceUrl": "https://arxiv.org/pdf/2406.10454v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2406.10454v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2406.10454",
      "sha256": "94c5fe16631e2d1c5b5bdd8326adda17c719ad63b2630979ca6aa9e0a7af4dd2",
      "bytes": 3711077,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:37:00.889735+00:00",
      "publicationDate": "2024/06/15",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2406.10454",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2406.10454",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2406.10454",
      "pages": 17,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "HumanPlus: Humanoid Shadowing and Imitation from Humans",
      "sourceVersion": "2406.10454v1",
      "sourceVersionDate": "2024/06/15",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.953855+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2406.10454"
    },
    {
      "id": "arxiv-2406.09246",
      "originalSourceUrl": "https://arxiv.org/pdf/2406.09246v3",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2406.09246v3",
      "finalDownloadUrl": "https://arxiv.org/pdf/2406.09246",
      "sha256": "353c37df34458f12f969b14dfd8b77175b727b9cddea7bb891759beddeefe1be",
      "bytes": 13240309,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:37:01.082684+00:00",
      "publicationDate": "2024/06/13",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2406.09246",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2406.09246",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2406.09246",
      "pages": 37,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "OpenVLA: An Open-Source Vision-Language-Action Model",
      "sourceVersion": "2406.09246v3",
      "sourceVersionDate": "2024/09/05",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.964446+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2406.09246"
    },
    {
      "id": "arxiv-2406.08858",
      "originalSourceUrl": "https://arxiv.org/pdf/2406.08858v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2406.08858v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2406.08858",
      "sha256": "bedce4c95c9776d64cd29587029c1f4d8171ad20f45017493627b27eb6b3138e",
      "bytes": 8193229,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:37:24.379623+00:00",
      "publicationDate": "2024/06/13",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2406.08858",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2406.08858",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2406.08858",
      "pages": 25,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning",
      "sourceVersion": "2406.08858v1",
      "sourceVersionDate": "2024/06/13",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.972660+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2406.08858"
    },
    {
      "id": "arxiv-2406.02523",
      "originalSourceUrl": "https://arxiv.org/pdf/2406.02523v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2406.02523v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2406.02523",
      "sha256": "7aca93ca3f157e32a46e02d675b3b2c24e3073a7807c038f7f566b73db87bde3",
      "bytes": 8307032,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:37:29.645195+00:00",
      "publicationDate": "2024/06/04",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2406.02523",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2406.02523",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2406.02523",
      "pages": 16,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots",
      "sourceVersion": "2406.02523v1",
      "sourceVersionDate": "2024/06/04",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.979456+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2406.02523"
    },
    {
      "id": "arxiv-2405.12213",
      "originalSourceUrl": "https://arxiv.org/pdf/2405.12213v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2405.12213v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2405.12213",
      "sha256": "73bff297cfafe523319162124e6b7f96919c0930e0a380f307255c4c7464ac93",
      "bytes": 3675649,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:37:29.587866+00:00",
      "publicationDate": "2024/05/20",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2405.12213",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2405.12213",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2405.12213",
      "pages": 17,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Octo: An Open-Source Generalist Robot Policy",
      "sourceVersion": "2405.12213v2",
      "sourceVersionDate": "2024/05/26",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.983025+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2405.12213"
    },
    {
      "id": "arxiv-2404.12377",
      "originalSourceUrl": "https://arxiv.org/pdf/2404.12377v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2404.12377v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2404.12377",
      "sha256": "7faf7287c5920d0c16b1f55849a214d97b8355af621632176178860d07b237e0",
      "bytes": 2747356,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:37:33.902586+00:00",
      "publicationDate": "2024/04/18",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2404.12377",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2404.12377",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2404.12377",
      "pages": 12,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "RoboDreamer: Learning Compositional World Models for Robot Imagination",
      "sourceVersion": "2404.12377v1",
      "sourceVersionDate": "2024/04/18",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.986124+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2404.12377"
    },
    {
      "id": "arxiv-2404.05695",
      "originalSourceUrl": "https://arxiv.org/pdf/2404.05695v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2404.05695v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2404.05695",
      "sha256": "f5a95d5797dc0b788087fc454fef0923f4d5055a14d69645902c0fcbc96e097e",
      "bytes": 3893938,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:37:39.861664+00:00",
      "publicationDate": "2024/04/08",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2404.05695",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2404.05695",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2404.05695",
      "pages": 6,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer",
      "sourceVersion": "2404.05695v2",
      "sourceVersionDate": "2024/05/18",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.989559+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2404.05695"
    },
    {
      "id": "arxiv-2403.12945",
      "originalSourceUrl": "https://arxiv.org/pdf/2403.12945v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2403.12945v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2403.12945",
      "sha256": "9e40a9c934ce78ea315d2c05593d60f9e18edf6dcd3785cd66439518965c3b07",
      "bytes": 9707714,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:37:46.824880+00:00",
      "publicationDate": "2024/03/19",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2403.12945",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2403.12945",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2403.12945",
      "pages": 26,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset",
      "sourceVersion": "2403.12945v2",
      "sourceVersionDate": "2025/04/22",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:14.996561+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2403.12945"
    },
    {
      "id": "arxiv-2403.04436",
      "originalSourceUrl": "https://arxiv.org/pdf/2403.04436v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2403.04436v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2403.04436",
      "sha256": "78d380da6e28949275137a7dd46922116a81efdf417a02aa81c6f40c5bcade22",
      "bytes": 13325640,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:37:47.387849+00:00",
      "publicationDate": "2024/03/07",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2403.04436",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2403.04436",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2403.04436",
      "pages": 10,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation",
      "sourceVersion": "2403.04436v1",
      "sourceVersionDate": "2024/03/07",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.008460+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2403.04436"
    },
    {
      "id": "arxiv-2401.02117",
      "originalSourceUrl": "https://arxiv.org/pdf/2401.02117v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2401.02117v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2401.02117",
      "sha256": "ad457dae227c27b0c2a15badfea5abbc6b0802877b25feceedeb770f0ebdb604",
      "bytes": 4357808,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:37:52.014083+00:00",
      "publicationDate": "2024/01/04",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2401.02117",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2401.02117",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2401.02117",
      "pages": 20,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation",
      "sourceVersion": "2401.02117v1",
      "sourceVersionDate": "2024/01/04",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.012334+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2401.02117"
    },
    {
      "id": "arxiv-2310.16828",
      "originalSourceUrl": "https://arxiv.org/pdf/2310.16828v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2310.16828v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2310.16828",
      "sha256": "99832c555b66665ad1e26cd48e75ea9dda4f3750175b993e7ed5b8dfe399b9e0",
      "bytes": 7858004,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:37:56.339041+00:00",
      "publicationDate": "2023/10/25",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2310.16828",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2310.16828",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2310.16828",
      "pages": 31,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "TD-MPC2: Scalable, Robust World Models for Continuous Control",
      "sourceVersion": "2310.16828v2",
      "sourceVersionDate": "2024/03/21",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.018684+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2310.16828"
    },
    {
      "id": "arxiv-2310.08864",
      "originalSourceUrl": "https://arxiv.org/pdf/2310.08864v9",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2310.08864v9",
      "finalDownloadUrl": "https://arxiv.org/pdf/2310.08864",
      "sha256": "13f16aff5afdee583dc25b3c570e9bb0cf6baefb59b539928d919588cd8d9246",
      "bytes": 4011306,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:37:56.305186+00:00",
      "publicationDate": "2023/10/13",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2310.08864",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2310.08864",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2310.08864",
      "pages": 12,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Open X-Embodiment: Robotic Learning Datasets and RT-X Models",
      "sourceVersion": "2310.08864v9",
      "sourceVersionDate": "2025/05/14",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.022749+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2310.08864"
    },
    {
      "id": "arxiv-2310.06114",
      "originalSourceUrl": "https://arxiv.org/pdf/2310.06114v3",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2310.06114v3",
      "finalDownloadUrl": "https://arxiv.org/pdf/2310.06114",
      "sha256": "956d21809f36cc107c82b3a32177ea555cacf032b3bde014fed1b958bc09c295",
      "bytes": 38316042,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:38:05.692358+00:00",
      "publicationDate": "2023/10/09",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2310.06114",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2310.06114",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2310.06114",
      "pages": 25,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Learning Interactive Real-World Simulators",
      "sourceVersion": "2310.06114v3",
      "sourceVersionDate": "2024/09/26",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.059507+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2310.06114"
    },
    {
      "id": "arxiv-2307.15818",
      "originalSourceUrl": "https://arxiv.org/pdf/2307.15818v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2307.15818v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2307.15818",
      "sha256": "0a62dc36bbbfdea232ad45a0ab75c82e9cf535b55333ff22c02d5da1897ccac3",
      "bytes": 15668163,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:38:09.098735+00:00",
      "publicationDate": "2023/07/28",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2307.15818",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2307.15818",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2307.15818",
      "pages": 26,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control",
      "sourceVersion": "2307.15818v1",
      "sourceVersionDate": "2023/07/28",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.072016+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2307.15818"
    },
    {
      "id": "arxiv-2306.11706",
      "originalSourceUrl": "https://arxiv.org/pdf/2306.11706v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2306.11706v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2306.11706",
      "sha256": "ec66c1579baaada787820abf4ce99a9a59143b583ddcc6dfc4814623d1969831",
      "bytes": 26404959,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:38:09.321507+00:00",
      "publicationDate": "2023/06/20",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2306.11706",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2306.11706",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2306.11706",
      "pages": 60,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation",
      "sourceVersion": "2306.11706v2",
      "sourceVersionDate": "2023/12/22",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.094056+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2306.11706"
    },
    {
      "id": "arxiv-2306.03310",
      "originalSourceUrl": "https://arxiv.org/pdf/2306.03310v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2306.03310v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2306.03310",
      "sha256": "ff7d943e2eb37760df684f3ae2931a5a35ef8ea465bd387e62afe49507b8e414",
      "bytes": 37420885,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:38:17.540735+00:00",
      "publicationDate": "2023/06/05",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2306.03310",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2306.03310",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2306.03310",
      "pages": 44,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning",
      "sourceVersion": "2306.03310v2",
      "sourceVersionDate": "2023/10/14",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.129902+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2306.03310"
    },
    {
      "id": "arxiv-2305.12127",
      "originalSourceUrl": "https://arxiv.org/pdf/2305.12127v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2305.12127v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2305.12127",
      "sha256": "66bc06ade6905f17a4dbb4b15a94cd2eb88129c56be3eb1d2fe1351d72304722",
      "bytes": 3619977,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:38:20.886921+00:00",
      "publicationDate": "2023/05/20",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2305.12127",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2305.12127",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2305.12127",
      "pages": 11,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "DexPBT: Scaling up Dexterous Manipulation for Hand-Arm Systems with Population Based Training",
      "sourceVersion": "2305.12127v1",
      "sourceVersionDate": "2023/05/20",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.135260+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2305.12127"
    },
    {
      "id": "arxiv-2305.05706",
      "originalSourceUrl": "https://arxiv.org/pdf/2305.05706v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2305.05706v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2305.05706",
      "sha256": "44354c0496a14f9ef90e19cd93f1521075adb6daff5f0a882cc045a649fbff7e",
      "bytes": 4578047,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:38:21.152049+00:00",
      "publicationDate": "2023/05/09",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2305.05706",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2305.05706",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2305.05706",
      "pages": 11,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objects",
      "sourceVersion": "2305.05706v1",
      "sourceVersionDate": "2023/05/09",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.139975+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2305.05706"
    },
    {
      "id": "arxiv-2304.13705",
      "originalSourceUrl": "https://arxiv.org/pdf/2304.13705v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2304.13705v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2304.13705",
      "sha256": "2e2fe25860f5f9cee9e655a2714e9f2264a7a5078bcd267c16d3f39af461345a",
      "bytes": 5353485,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:38:30.513035+00:00",
      "publicationDate": "2023/04/23",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2304.13705",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2304.13705",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2304.13705",
      "pages": 18,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware",
      "sourceVersion": "2304.13705v1",
      "sourceVersionDate": "2023/04/23",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.144295+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2304.13705"
    },
    {
      "id": "arxiv-2303.04137",
      "originalSourceUrl": "https://arxiv.org/pdf/2303.04137v4",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2303.04137v4",
      "finalDownloadUrl": "https://arxiv.org/pdf/2303.04137v4",
      "sha256": "75a57946e2cef790775ca5c667b00befc8ea7d64c3a02c5ced3e3d173354640c",
      "bytes": 5834180,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:38:30.683550+00:00",
      "publicationDate": "2023/03/07",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2303.04137v4",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2303.04137v4",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2303.04137v4",
      "pages": 16,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Diffusion Policy: Visuomotor Policy Learning via Action Diffusion",
      "sourceVersion": "2303.04137v4",
      "sourceVersionDate": "2023/06/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.149809+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2303.04137v4"
    },
    {
      "id": "arxiv-2303.03381",
      "originalSourceUrl": "https://arxiv.org/pdf/2303.03381v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2303.03381v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2303.03381",
      "sha256": "9b310e368242b5d3856bcbe55990261fdd2072fba966c5f9887cc896c5e5ee5a",
      "bytes": 9586709,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:38:40.921731+00:00",
      "publicationDate": "2023/03/06",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2303.03381",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2303.03381",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2303.03381",
      "pages": 32,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Real-World Humanoid Locomotion with Reinforcement Learning",
      "sourceVersion": "2303.03381v2",
      "sourceVersionDate": "2023/12/14",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.166464+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2303.03381"
    },
    {
      "id": "arxiv-2303.03378",
      "originalSourceUrl": "https://arxiv.org/pdf/2303.03378v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2303.03378v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2303.03378",
      "sha256": "535cc3c7fe1ae7428b9ac7d6a3738a0529975aadc372b2229ea0cb2ce724576a",
      "bytes": 10707237,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:38:35.734824+00:00",
      "publicationDate": "2023/03/06",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2303.03378",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2303.03378",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2303.03378",
      "pages": 18,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "PaLM-E: An Embodied Multimodal Language Model",
      "sourceVersion": "2303.03378v1",
      "sourceVersionDate": "2023/03/06",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.158836+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2303.03378"
    },
    {
      "id": "arxiv-2301.04104",
      "originalSourceUrl": "https://arxiv.org/pdf/2301.04104v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2301.04104v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2301.04104",
      "sha256": "d0385798e8bada8e81b915c1743be81d9ce8776f12ed937e09351995e099ce37",
      "bytes": 2874717,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:38:40.867947+00:00",
      "publicationDate": "2023/01/10",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2301.04104",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2301.04104",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2301.04104",
      "pages": 40,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Mastering Diverse Domains through World Models",
      "sourceVersion": "2301.04104v2",
      "sourceVersionDate": "2024/04/17",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.169273+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2301.04104"
    },
    {
      "id": "arxiv-2212.06817",
      "originalSourceUrl": "https://arxiv.org/pdf/2212.06817v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2212.06817v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2212.06817",
      "sha256": "81efe669c8fa50ffc7097886dc78a442fa7a8f7f2451684b93069cb9fbeda767",
      "bytes": 14672588,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:38:49.019582+00:00",
      "publicationDate": "2022/12/13",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2212.06817",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2212.06817",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2212.06817",
      "pages": 31,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "RT-1: Robotics Transformer for Real-World Control at Scale",
      "sourceVersion": "2212.06817v2",
      "sourceVersionDate": "2023/08/11",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.180896+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2212.06817"
    },
    {
      "id": "arxiv-2211.09423",
      "originalSourceUrl": "https://arxiv.org/pdf/2211.09423v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2211.09423v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2211.09423",
      "sha256": "c77516db0f09ad6c3964ee279b56c4db445502827af860fa3c1f5c7c517ae93d",
      "bytes": 6899060,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:38:52.686379+00:00",
      "publicationDate": "2022/11/17",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2211.09423",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2211.09423",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2211.09423",
      "pages": 13,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation",
      "sourceVersion": "2211.09423v2",
      "sourceVersionDate": "2022/11/18",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.187062+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2211.09423"
    },
    {
      "id": "arxiv-2210.10044",
      "originalSourceUrl": "https://arxiv.org/pdf/2210.10044v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2210.10044v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2210.10044",
      "sha256": "836a835e9d8939c6261b3ca597a19bbafa3540dbde722c651c2dbe035f1f1541",
      "bytes": 7922418,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:38:53.010434+00:00",
      "publicationDate": "2022/10/18",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2210.10044",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2210.10044",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2210.10044",
      "pages": 16,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion",
      "sourceVersion": "2210.10044v1",
      "sourceVersionDate": "2022/10/18",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.193366+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2210.10044"
    },
    {
      "id": "arxiv-2210.05714",
      "originalSourceUrl": "https://arxiv.org/pdf/2210.05714v4",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2210.05714v4",
      "finalDownloadUrl": "https://arxiv.org/pdf/2210.05714",
      "sha256": "c7bb57c0defb3761526f740d187d215980b6a757eec14c7948d2d8c73c7b421d",
      "bytes": 6821714,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:39:01.464670+00:00",
      "publicationDate": "2022/10/11",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2210.05714",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2210.05714",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2210.05714",
      "pages": 11,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Visual Language Maps for Robot Navigation",
      "sourceVersion": "2210.05714v4",
      "sourceVersionDate": "2023/03/08",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.198818+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2210.05714"
    },
    {
      "id": "arxiv-2210.03094",
      "originalSourceUrl": "https://arxiv.org/pdf/2210.03094v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2210.03094v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2210.03094",
      "sha256": "cf849f80368749b0310b43117519ce0abff3e8ae49744e78c4a29b9d17f0695f",
      "bytes": 30270724,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:39:05.060828+00:00",
      "publicationDate": "2022/10/06",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2210.03094",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2210.03094",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2210.03094",
      "pages": 48,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "VIMA: General Robot Manipulation with Multimodal Prompts",
      "sourceVersion": "2210.03094v2",
      "sourceVersionDate": "2023/05/28",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.227766+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2210.03094"
    },
    {
      "id": "arxiv-2209.00588",
      "originalSourceUrl": "https://arxiv.org/pdf/2209.00588v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2209.00588v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2209.00588",
      "sha256": "6b583542ba35dc99a36127dd3b7650aac5d28479f3fe0e5e47f741768ae587b4",
      "bytes": 655408,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:39:04.422147+00:00",
      "publicationDate": "2022/09/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2209.00588",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2209.00588",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2209.00588",
      "pages": 21,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Transformers are Sample-Efficient World Models",
      "sourceVersion": "2209.00588v2",
      "sourceVersionDate": "2023/03/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.231129+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2209.00588"
    },
    {
      "id": "arxiv-2206.14176",
      "originalSourceUrl": "https://arxiv.org/pdf/2206.14176v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2206.14176v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2206.14176",
      "sha256": "2ee10ae0961bef97ca522bb7ee5b7514e7a918a637dedad569b572b18bccb35e",
      "bytes": 3126052,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:39:12.926681+00:00",
      "publicationDate": "2022/06/28",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2206.14176",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2206.14176",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2206.14176",
      "pages": 15,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "DayDreamer: World Models for Physical Robot Learning",
      "sourceVersion": "2206.14176v1",
      "sourceVersionDate": "2022/06/28",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.234333+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2206.14176"
    },
    {
      "id": "arxiv-2205.01906",
      "originalSourceUrl": "https://arxiv.org/pdf/2205.01906v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2205.01906v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2205.01906",
      "sha256": "e4151dfddd0f79ef496092b58c10ef67b519e9a5be3b4d5b2067c575124050c7",
      "bytes": 24478689,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:39:18.131012+00:00",
      "publicationDate": "2022/05/04",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2205.01906",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2205.01906",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2205.01906",
      "pages": 18,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters",
      "sourceVersion": "2205.01906v2",
      "sourceVersionDate": "2022/05/05",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.251311+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2205.01906"
    },
    {
      "id": "arxiv-2204.01691",
      "originalSourceUrl": "https://arxiv.org/pdf/2204.01691v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2204.01691v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2204.01691",
      "sha256": "48c22d36a044bbbd34e640beb1db4fb4ba57e74d97fefa0fb121d55c31282312",
      "bytes": 12827088,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:39:17.962799+00:00",
      "publicationDate": "2022/04/04",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2204.01691",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2204.01691",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2204.01691",
      "pages": 34,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Do As I Can, Not As I Say: Grounding Language in Robotic Affordances",
      "sourceVersion": "2204.01691v2",
      "sourceVersionDate": "2022/08/16",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.262221+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2204.01691"
    },
    {
      "id": "arxiv-2203.04955",
      "originalSourceUrl": "https://arxiv.org/pdf/2203.04955v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2203.04955v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2203.04955",
      "sha256": "b80e9fc9eaebfa43ad30641ebb0327346998e604cd7421ae44701ef373b501aa",
      "bytes": 12584890,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:39:23.007731+00:00",
      "publicationDate": "2022/03/09",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2203.04955",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2203.04955",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2203.04955",
      "pages": 20,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Temporal Difference Learning for Model Predictive Control",
      "sourceVersion": "2203.04955v2",
      "sourceVersionDate": "2022/07/19",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.271981+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2203.04955"
    },
    {
      "id": "arxiv-2109.12098",
      "originalSourceUrl": "https://arxiv.org/pdf/2109.12098v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2109.12098v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2109.12098",
      "sha256": "3cc19664beabda203cb1a1ad86659f75f60a099189820d92d59d20067c9ab003",
      "bytes": 8143919,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:39:27.363965+00:00",
      "publicationDate": "2021/09/24",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2109.12098",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2109.12098",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2109.12098",
      "pages": 24,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "CLIPort: What and Where Pathways for Robotic Manipulation",
      "sourceVersion": "2109.12098v1",
      "sourceVersionDate": "2021/09/24",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.279694+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2109.12098"
    },
    {
      "id": "arxiv-2109.11978",
      "originalSourceUrl": "https://arxiv.org/pdf/2109.11978v3",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2109.11978v3",
      "finalDownloadUrl": "https://arxiv.org/pdf/2109.11978",
      "sha256": "48014ee8af3e5a7fc26de2a5aac0de9ad593725075627c1a210d9d0f1e4ee62a",
      "bytes": 38462407,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:39:32.104150+00:00",
      "publicationDate": "2021/09/24",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2109.11978",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2109.11978",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2109.11978",
      "pages": 14,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning",
      "sourceVersion": "2109.11978v3",
      "sourceVersionDate": "2022/08/19",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.316275+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2109.11978"
    },
    {
      "id": "arxiv-2108.05877",
      "originalSourceUrl": "https://arxiv.org/pdf/2108.05877v5",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2108.05877v5",
      "finalDownloadUrl": "https://arxiv.org/pdf/2108.05877",
      "sha256": "9b2e0e5207253be4594aaf3dfca6db8d38527e937738239409e5536ef3cf57c4",
      "bytes": 8540406,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:39:35.269164+00:00",
      "publicationDate": "2021/08/12",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2108.05877",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2108.05877",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2108.05877",
      "pages": 25,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "DexMV: Imitation Learning for Dexterous Manipulation from Human Videos",
      "sourceVersion": "2108.05877v5",
      "sourceVersionDate": "2022/07/06",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.324399+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2108.05877"
    },
    {
      "id": "arxiv-2108.03298",
      "originalSourceUrl": "https://arxiv.org/pdf/2108.03298v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2108.03298v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2108.03298",
      "sha256": "18283ff9cbb9645de4ccf32ca2de472f452e89761287e7ed578e3a1066bea5f1",
      "bytes": 10782355,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:39:39.856810+00:00",
      "publicationDate": "2021/08/06",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2108.03298",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2108.03298",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2108.03298",
      "pages": 36,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "What Matters in Learning from Offline Human Demonstrations for Robot Manipulation",
      "sourceVersion": "2108.03298v2",
      "sourceVersionDate": "2021/09/25",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.332689+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2108.03298"
    },
    {
      "id": "arxiv-2107.06829",
      "originalSourceUrl": "https://arxiv.org/pdf/2107.06829v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2107.06829v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2107.06829",
      "sha256": "ba5072e06e75dec5222bcb528143f3aa3238d6f6692bac1e22a9fe1bc55a15dd",
      "bytes": 13481318,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:39:45.184925+00:00",
      "publicationDate": "2021/07/14",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2107.06829",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2107.06829",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2107.06829",
      "pages": 19,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "FAST-LIO2: Fast Direct LiDAR-inertial Odometry",
      "sourceVersion": "2107.06829v1",
      "sourceVersionDate": "2021/07/14",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.342868+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2107.06829"
    },
    {
      "id": "arxiv-2107.04034",
      "originalSourceUrl": "https://arxiv.org/pdf/2107.04034v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2107.04034v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2107.04034",
      "sha256": "d8660da881851756287efab24d85f5c629ba97878f70297eb429a8e8a9a57846",
      "bytes": 16534863,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:39:45.178010+00:00",
      "publicationDate": "2021/07/08",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2107.04034",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2107.04034",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2107.04034",
      "pages": 15,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "RMA: Rapid Motor Adaptation for Legged Robots",
      "sourceVersion": "2107.04034v1",
      "sourceVersionDate": "2021/07/08",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.355542+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2107.04034"
    },
    {
      "id": "arxiv-2104.02180",
      "originalSourceUrl": "https://arxiv.org/pdf/2104.02180v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2104.02180v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2104.02180",
      "sha256": "93d9e8e40b3908d65e8b88ae3dcbe8d4cd69071d13f3234ad927462477472a29",
      "bytes": 8715012,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:39:54.872931+00:00",
      "publicationDate": "2021/04/05",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2104.02180",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2104.02180",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2104.02180",
      "pages": 20,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control",
      "sourceVersion": "2104.02180v2",
      "sourceVersionDate": "2022/05/12",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.362357+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2104.02180"
    },
    {
      "id": "arxiv-2010.14406",
      "originalSourceUrl": "https://arxiv.org/pdf/2010.14406v3",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2010.14406v3",
      "finalDownloadUrl": "https://arxiv.org/pdf/2010.14406",
      "sha256": "3a5e78b5c8881863845c46bda0bf8c9071aa79a59a6f9a9f4d8732690482b228",
      "bytes": 3781112,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:39:54.796116+00:00",
      "publicationDate": "2020/10/27",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2010.14406",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2010.14406",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2010.14406",
      "pages": 23,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Transporter Networks: Rearranging the Visual World for Robotic Manipulation",
      "sourceVersion": "2010.14406v3",
      "sourceVersionDate": "2022/01/05",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.366398+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2010.14406"
    },
    {
      "id": "arxiv-2010.02193",
      "originalSourceUrl": "https://arxiv.org/pdf/2010.02193v4",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2010.02193v4",
      "finalDownloadUrl": "https://arxiv.org/pdf/2010.02193",
      "sha256": "037dce26de328dd86ce4ab71dfb54f44513fef49a02f2995a1c05848ccef158f",
      "bytes": 5261247,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:39:58.472997+00:00",
      "publicationDate": "2020/10/05",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2010.02193",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2010.02193",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2010.02193",
      "pages": 26,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Mastering Atari with Discrete World Models",
      "sourceVersion": "2010.02193v4",
      "sourceVersionDate": "2022/02/12",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.371141+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2010.02193"
    },
    {
      "id": "arxiv-2007.11898",
      "originalSourceUrl": "https://arxiv.org/pdf/2007.11898v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2007.11898v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2007.11898",
      "sha256": "4d119517be7565c9651fbf1e36a330d605b7a534d738558858c96feca7b99156",
      "bytes": 5049669,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:40:02.753784+00:00",
      "publicationDate": "2020/07/23",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2007.11898",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2007.11898",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2007.11898",
      "pages": 18,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM",
      "sourceVersion": "2007.11898v2",
      "sourceVersionDate": "2021/04/23",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.375884+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2007.11898"
    },
    {
      "id": "arxiv-2007.00643",
      "originalSourceUrl": "https://arxiv.org/pdf/2007.00643v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2007.00643v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2007.00643",
      "sha256": "abe66c10e6d8115852edf797cc02bd09b15e587e1690573c4582cf7d714621f2",
      "bytes": 1965159,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:40:12.576230+00:00",
      "publicationDate": "2020/07/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2007.00643",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2007.00643",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2007.00643",
      "pages": 11,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Object Goal Navigation using Goal-Oriented Semantic Exploration",
      "sourceVersion": "2007.00643v2",
      "sourceVersionDate": "2020/07/02",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.385579+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2007.00643"
    },
    {
      "id": "arxiv-2007.00258",
      "originalSourceUrl": "https://arxiv.org/pdf/2007.00258v3",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2007.00258v3",
      "finalDownloadUrl": "https://arxiv.org/pdf/2007.00258",
      "sha256": "8ad11438fc0849de88b1604932f8bfd2732aee640aaf5fb41974b34f555c86f6",
      "bytes": 4368703,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:40:07.589827+00:00",
      "publicationDate": "2020/07/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2007.00258",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2007.00258",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2007.00258",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping",
      "sourceVersion": "2007.00258v3",
      "sourceVersionDate": "2020/07/14",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.383002+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2007.00258"
    },
    {
      "id": "arxiv-1912.01603",
      "originalSourceUrl": "https://arxiv.org/pdf/1912.01603v3",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1912.01603v3",
      "finalDownloadUrl": "https://arxiv.org/pdf/1912.01603",
      "sha256": "318891d59ba0065f57eb0e735735700e5eb528f53bf08b81c773437385586c64",
      "bytes": 1999946,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:40:12.645695+00:00",
      "publicationDate": "2019/12/03",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1912.01603",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1912.01603",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1912.01603",
      "pages": 20,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Dream to Control: Learning Behaviors by Latent Imagination",
      "sourceVersion": "1912.01603v3",
      "sourceVersionDate": "2020/03/17",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.388006+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1912.01603"
    },
    {
      "id": "arxiv-1910.07113",
      "originalSourceUrl": "https://arxiv.org/pdf/1910.07113v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1910.07113v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/1910.07113",
      "sha256": "2a6fe43013ddc8d148b0cdebc8468dfe83d11319ed626a1aeaa79b510e2ed48c",
      "bytes": 5194320,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:40:21.511874+00:00",
      "publicationDate": "2019/10/16",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1910.07113",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1910.07113",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1910.07113",
      "pages": 51,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Solving Rubik's Cube with a Robot Hand",
      "sourceVersion": "1910.07113v1",
      "sourceVersionDate": "2019/10/16",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.392905+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1910.07113"
    },
    {
      "id": "arxiv-1910.03135",
      "originalSourceUrl": "https://arxiv.org/pdf/1910.03135v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1910.03135v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/1910.03135",
      "sha256": "d04e6f165fdfd64b02de0545d69feef99ae77351c3635f9190394594aad472d1",
      "bytes": 5763327,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:40:21.531823+00:00",
      "publicationDate": "2019/10/07",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1910.03135",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1910.03135",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1910.03135",
      "pages": 18,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System",
      "sourceVersion": "1910.03135v2",
      "sourceVersionDate": "2019/10/14",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.401318+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1910.03135"
    },
    {
      "id": "arxiv-1904.01201",
      "originalSourceUrl": "https://arxiv.org/pdf/1904.01201v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1904.01201v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/1904.01201",
      "sha256": "53485f2ed9af000b4f929be140c94e9bc097a59b69a0e5ae847446c0bb947e18",
      "bytes": 6108339,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:40:27.267804+00:00",
      "publicationDate": "2019/04/02",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1904.01201",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1904.01201",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1904.01201",
      "pages": 17,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Habitat: A Platform for Embodied AI Research",
      "sourceVersion": "1904.01201v2",
      "sourceVersionDate": "2019/11/25",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.406968+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1904.01201"
    },
    {
      "id": "arxiv-1901.08652",
      "originalSourceUrl": "https://arxiv.org/pdf/1901.08652v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1901.08652v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/1901.08652",
      "sha256": "c69eda2f422866925c3567ead246be231928af51dcdfa97f849222118d75ae45",
      "bytes": 7975310,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:40:49.265622+00:00",
      "publicationDate": "2019/01/24",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1901.08652",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1901.08652",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1901.08652",
      "pages": 20,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Learning agile and dynamic motor skills for legged robots",
      "sourceVersion": "1901.08652v1",
      "sourceVersionDate": "2019/01/24",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.417780+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1901.08652"
    },
    {
      "id": "arxiv-2403.06341",
      "originalSourceUrl": "https://arxiv.org/pdf/2403.06341v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2403.06341v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2403.06341",
      "sha256": "b6f641d5d2ed41e301940d57f1fb59a3cb6029f5ab04a21dff0c28013b19abe6",
      "bytes": 23360699,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:40:54.282655+00:00",
      "publicationDate": "2024/03/10",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2403.06341",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2403.06341",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2403.06341",
      "pages": 40,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "RTAB-Map as an Open-Source Lidar and Visual SLAM Library for Large-Scale and Long-Term Online Operation",
      "sourceVersion": "2403.06341v1",
      "sourceVersionDate": "2024/03/10",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.436573+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2403.06341"
    },
    {
      "id": "arxiv-1811.04551",
      "originalSourceUrl": "https://arxiv.org/pdf/1811.04551v5",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1811.04551v5",
      "finalDownloadUrl": "https://arxiv.org/pdf/1811.04551",
      "sha256": "abac727526e6a45669d3ab9957126587e22aacf4dc9bcd60ffe5c853108e5bcc",
      "bytes": 3146899,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:40:53.602154+00:00",
      "publicationDate": "2018/11/12",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1811.04551",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1811.04551",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1811.04551",
      "pages": 20,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Learning Latent Dynamics for Planning from Pixels",
      "sourceVersion": "1811.04551v5",
      "sourceVersionDate": "2019/06/04",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.440825+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1811.04551"
    },
    {
      "id": "arxiv-1808.00177",
      "originalSourceUrl": "https://arxiv.org/pdf/1808.00177v5",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1808.00177v5",
      "finalDownloadUrl": "https://arxiv.org/pdf/1808.00177",
      "sha256": "da6ec44dd0941d674ec58334ff630f83d7bd19e6062ab2837ccfa0b3b94f6f73",
      "bytes": 4590851,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:41:01.115298+00:00",
      "publicationDate": "2018/08/01",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1808.00177",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1808.00177",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1808.00177",
      "pages": 27,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Learning Dexterous In-Hand Manipulation",
      "sourceVersion": "1808.00177v5",
      "sourceVersionDate": "2019/01/18",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.446696+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1808.00177"
    },
    {
      "id": "arxiv-1806.10293",
      "originalSourceUrl": "https://arxiv.org/pdf/1806.10293v3",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1806.10293v3",
      "finalDownloadUrl": "https://arxiv.org/pdf/1806.10293",
      "sha256": "1482043a0e94f30c0db5b1841574a81a44eeaa47154ca99492e31c3706b89c75",
      "bytes": 5491270,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:41:05.494749+00:00",
      "publicationDate": "2018/06/27",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1806.10293",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1806.10293",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1806.10293",
      "pages": 23,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation",
      "sourceVersion": "1806.10293v3",
      "sourceVersionDate": "2018/11/28",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.452254+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1806.10293"
    },
    {
      "id": "arxiv-1804.02717",
      "originalSourceUrl": "https://arxiv.org/pdf/1804.02717v3",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1804.02717v3",
      "finalDownloadUrl": "https://arxiv.org/pdf/1804.02717",
      "sha256": "4bd4cc353bd2dc19da99bb21a254cbfdb9840e49940ce69d484eb6d45bfa348f",
      "bytes": 7770304,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:41:05.631393+00:00",
      "publicationDate": "2018/04/08",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1804.02717",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1804.02717",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1804.02717",
      "pages": 18,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills",
      "sourceVersion": "1804.02717v3",
      "sourceVersionDate": "2018/07/27",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.460323+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1804.02717"
    },
    {
      "id": "arxiv-1803.10122",
      "originalSourceUrl": "https://arxiv.org/pdf/1803.10122v4",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1803.10122v4",
      "finalDownloadUrl": "https://arxiv.org/pdf/1803.10122",
      "sha256": "b0c1e30aab53efd28ddf61d661f680150918d4d03b77bae62bc52d62dbd76cce",
      "bytes": 3147467,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:41:12.795754+00:00",
      "publicationDate": "2018/03/27",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1803.10122",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1803.10122",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1803.10122",
      "pages": 21,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "World Models",
      "sourceVersion": "1803.10122v4",
      "sourceVersionDate": "2018/05/09",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.466480+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1803.10122"
    },
    {
      "id": "arxiv-1801.01290",
      "originalSourceUrl": "https://arxiv.org/pdf/1801.01290v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1801.01290v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/1801.01290",
      "sha256": "5c33fae017d02f7025730f05198d4a6b103402822c8bbf48cbc5d8a0474c336a",
      "bytes": 4388102,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:41:16.963899+00:00",
      "publicationDate": "2018/01/04",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1801.01290",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1801.01290",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1801.01290",
      "pages": 14,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor",
      "sourceVersion": "1801.01290v2",
      "sourceVersionDate": "2018/08/08",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.471394+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1801.01290"
    },
    {
      "id": "arxiv-1711.07280",
      "originalSourceUrl": "https://arxiv.org/pdf/1711.07280v3",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1711.07280v3",
      "finalDownloadUrl": "https://arxiv.org/pdf/1711.07280",
      "sha256": "b7589865ee573d4753ee9e25bdc494cbbb199e6ec17d0a349091aed0fd86c420",
      "bytes": 9720283,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:41:16.979569+00:00",
      "publicationDate": "2017/11/20",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1711.07280",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1711.07280",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1711.07280",
      "pages": 13,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments",
      "sourceVersion": "1711.07280v3",
      "sourceVersionDate": "2018/04/05",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.481156+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1711.07280"
    },
    {
      "id": "arxiv-1708.03852",
      "originalSourceUrl": "https://arxiv.org/pdf/1708.03852v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1708.03852v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/1708.03852",
      "sha256": "1f44f92f057cbb05a6570f14d2fe5cae2b9736198a8eeca7c93438adbc38a087",
      "bytes": 4382711,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:41:27.278976+00:00",
      "publicationDate": "2017/08/13",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1708.03852",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1708.03852",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1708.03852",
      "pages": 17,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator",
      "sourceVersion": "1708.03852v1",
      "sourceVersionDate": "2017/08/13",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.485710+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1708.03852"
    },
    {
      "id": "arxiv-1707.06347",
      "originalSourceUrl": "https://arxiv.org/pdf/1707.06347v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1707.06347v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/1707.06347",
      "sha256": "e78feadadbdbb0b601b3c2bcc81404722cd431a489b307545f9b7bea1e8c4f5b",
      "bytes": 2923532,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:41:27.291864+00:00",
      "publicationDate": "2017/07/20",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1707.06347",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1707.06347",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1707.06347",
      "pages": 12,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Proximal Policy Optimization Algorithms",
      "sourceVersion": "1707.06347v2",
      "sourceVersionDate": "2017/08/28",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.489201+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1707.06347"
    },
    {
      "id": "arxiv-1703.06907",
      "originalSourceUrl": "https://arxiv.org/pdf/1703.06907v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1703.06907v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/1703.06907",
      "sha256": "3fc98c5f4cea050686d45858e647e1b704492121fdae80f8fcd5d560c107f11f",
      "bytes": 4066798,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:41:31.581183+00:00",
      "publicationDate": "2017/03/20",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1703.06907",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1703.06907",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1703.06907",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World",
      "sourceVersion": "1703.06907v1",
      "sourceVersionDate": "2017/03/20",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.495176+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1703.06907"
    },
    {
      "id": "arxiv-1610.06475",
      "originalSourceUrl": "https://arxiv.org/pdf/1610.06475v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1610.06475v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/1610.06475",
      "sha256": "2b94552a20378d6dfbe863ba7317d4a86874fe54e43ca8b918abefcbdc64ce24",
      "bytes": 4187799,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:41:34.914844+00:00",
      "publicationDate": "2016/10/20",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1610.06475",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1610.06475",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1610.06475",
      "pages": 9,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras",
      "sourceVersion": "1610.06475v2",
      "sourceVersionDate": "2017/06/19",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.501740+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1610.06475"
    },
    {
      "id": "arxiv-1610.00696",
      "originalSourceUrl": "https://arxiv.org/pdf/1610.00696v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1610.00696v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/1610.00696",
      "sha256": "c16bb0f44725a3a27307f790ffe31e032c21f4f90c9b182c0236266d3b783089",
      "bytes": 4135921,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:41:40.247254+00:00",
      "publicationDate": "2016/10/03",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1610.00696",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1610.00696",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1610.00696",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Deep Visual Foresight for Planning Robot Motion",
      "sourceVersion": "1610.00696v2",
      "sourceVersionDate": "2017/03/13",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.506225+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1610.00696"
    },
    {
      "id": "arxiv-1607.02565",
      "originalSourceUrl": "https://arxiv.org/pdf/1607.02565v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1607.02565v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/1607.02565",
      "sha256": "cd85260a38b0b5d0e82c85c37c3540c498a953e39a501d9af5192a35b8284223",
      "bytes": 7990289,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:41:45.251834+00:00",
      "publicationDate": "2016/07/09",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1607.02565",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1607.02565",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1607.02565",
      "pages": 17,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Direct Sparse Odometry",
      "sourceVersion": "1607.02565v2",
      "sourceVersionDate": "2016/10/07",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.514669+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1607.02565"
    },
    {
      "id": "cartographer-2016",
      "originalSourceUrl": "https://research.google.com/pubs/archive/45466.pdf",
      "finalDownloadUrl": "https://static.googleusercontent.com/media/research.google.com/en//pubs/archive/45466.pdf",
      "sha256": "351edb45cd478c8cf2e22e375b8565a7abb3455e92f45e7a7f4163130bde69a2",
      "bytes": 1207803,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:34:55.290308+00:00",
      "publicationDate": "2016",
      "publicationDateSourceUrl": "https://research.google/pubs/real-time-loop-closure-in-2d-lidar-slam/",
      "license": "IEEE copyright; public author-hosted copy. Redistribution permission not verified.",
      "licenseSourceUrl": "https://research.google/pubs/real-time-loop-closure-in-2d-lidar-slam/",
      "licenseStatus": "rights_notice_verified",
      "licenseScope": "paper; does not establish code license",
      "pages": 8,
      "sourceIdentityStatus": "title_match_in_pdf",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.517180+00:00"
    },
    {
      "id": "arxiv-1509.02971",
      "originalSourceUrl": "https://arxiv.org/pdf/1509.02971v6",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1509.02971v6",
      "finalDownloadUrl": "https://arxiv.org/pdf/1509.02971",
      "sha256": "34ef677ecdee8c2a72721c70c7d849191be72af39ac8691a12e8c2979a28feda",
      "bytes": 663643,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:41:45.150218+00:00",
      "publicationDate": "2015/09/09",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1509.02971",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1509.02971",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1509.02971",
      "pages": 14,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Continuous control with deep reinforcement learning",
      "sourceVersion": "1509.02971v6",
      "sourceVersionDate": "2019/07/05",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.518977+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1509.02971"
    },
    {
      "id": "arxiv-1504.00702",
      "originalSourceUrl": "https://arxiv.org/pdf/1504.00702v5",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1504.00702v5",
      "finalDownloadUrl": "https://arxiv.org/pdf/1504.00702",
      "sha256": "28ad13a058680cbf5c007c7fdf2f66330bef4b3efa7d1c06169680bc81758f41",
      "bytes": 6257924,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:41:53.409517+00:00",
      "publicationDate": "2015/04/02",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1504.00702",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1504.00702",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1504.00702",
      "pages": 40,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "End-to-End Training of Deep Visuomotor Policies",
      "sourceVersion": "1504.00702v5",
      "sourceVersionDate": "2016/04/19",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.525774+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1504.00702"
    },
    {
      "id": "arxiv-1502.00956",
      "originalSourceUrl": "https://arxiv.org/pdf/1502.00956v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1502.00956v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/1502.00956",
      "sha256": "442bcef21b04c007628c452e21b3122296e76fee727b1fc766e7d2b666ec3634",
      "bytes": 4202706,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:41:57.039400+00:00",
      "publicationDate": "2015/02/03",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1502.00956",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1502.00956",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1502.00956",
      "pages": 18,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "ORB-SLAM: a Versatile and Accurate Monocular SLAM System",
      "sourceVersion": "1502.00956v2",
      "sourceVersionDate": "2015/09/18",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.531881+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1502.00956"
    },
    {
      "id": "lsd-slam-2014",
      "originalSourceUrl": "https://jakobengel.github.io/pdf/engel14eccv.pdf",
      "finalDownloadUrl": "https://jakobengel.github.io/pdf/engel14eccv.pdf",
      "sha256": "9d39989b15d1847d51432e90ba02cf5c7ae2b04da478214cf3fa050d2c39c64a",
      "bytes": 11044034,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:35:03.754674+00:00",
      "publicationDate": null,
      "publicationDateSourceUrl": null,
      "license": null,
      "licenseSourceUrl": null,
      "licenseStatus": "not_verified",
      "pages": 16,
      "sourceIdentityStatus": "title_match_in_pdf",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.541917+00:00"
    },
    {
      "id": "loam-2014",
      "originalSourceUrl": "https://www.roboticsproceedings.org/rss10/p07.pdf",
      "finalDownloadUrl": "https://www.roboticsproceedings.org/rss10/p07.pdf",
      "sha256": "0d66f17eadd7770e5894df92a3ca854a9a53f366f2aec6a828eb1bbcd6e28941",
      "bytes": 3645860,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:35:12.791496+00:00",
      "publicationDate": "2014-07",
      "publicationDateSourceUrl": "https://www.roboticsproceedings.org/rss10/p07.html",
      "license": null,
      "licenseSourceUrl": null,
      "licenseStatus": "not_verified",
      "pages": 9,
      "sourceIdentityStatus": "title_match_in_pdf",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.545350+00:00"
    },
    {
      "id": "guided-policy-search",
      "originalSourceUrl": "https://proceedings.mlr.press/v28/levine13.pdf",
      "finalDownloadUrl": "https://proceedings.mlr.press/v28/levine13.pdf",
      "sha256": "f0ea0f19842973f8d675d6ba6dec5b6bfddc576211dadb0e02dccf452e97790a",
      "bytes": 1594905,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:35:28.946864+00:00",
      "publicationDate": "2013-06",
      "publicationDateSourceUrl": "https://proceedings.mlr.press/v28/levine13.html",
      "license": null,
      "licenseSourceUrl": null,
      "licenseStatus": "not_verified",
      "pages": 9,
      "sourceIdentityStatus": "title_match_in_pdf",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.550562+00:00"
    },
    {
      "id": "dmp",
      "originalSourceUrl": "https://www.pure.ed.ac.uk/ws/portalfiles/portal/7874487/NECO_a_00393.pdf",
      "finalDownloadUrl": "https://www.pure.ed.ac.uk/ws/portalfiles/portal/7874487/NECO_a_00393.pdf",
      "sha256": "3b7c8d3a141c7edd0253f8056dee39155fe9ed678da75676bb41a39324b534f4",
      "bytes": 2741402,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:35:21.171023+00:00",
      "publicationDate": "2013",
      "publicationDateSourceUrl": "https://www.pure.ed.ac.uk/ws/portalfiles/portal/7874487/NECO_a_00393.pdf",
      "license": "Copyright 2013 Massachusetts Institute of Technology; repository says rights retained by authors/copyright owners.",
      "licenseSourceUrl": "https://www.pure.ed.ac.uk/ws/portalfiles/portal/7874487/NECO_a_00393.pdf",
      "licenseStatus": "rights_notice_verified",
      "licenseScope": "paper; does not establish code license",
      "pages": 47,
      "sourceIdentityStatus": "title_match_in_pdf",
      "documentVersion": "Publisher PDF (version of record), with repository cover page",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.548147+00:00"
    },
    {
      "id": "arxiv-1011.0686",
      "originalSourceUrl": "https://arxiv.org/pdf/1011.0686v3",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1011.0686v3",
      "finalDownloadUrl": "https://arxiv.org/pdf/1011.0686",
      "sha256": "12b032cfd451b8ace4b18145dbe24382d2cbe2eda6b562331bc86799bbaafd5e",
      "bytes": 551229,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:41:57.020639+00:00",
      "publicationDate": "2010/11/02",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1011.0686",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1011.0686",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1011.0686",
      "pages": 9,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning",
      "sourceVersion": "1011.0686v3",
      "sourceVersionDate": "2011/03/16",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.553278+00:00",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1011.0686"
    },
    {
      "id": "ptam-2007",
      "originalSourceUrl": "https://www.robots.ox.ac.uk/~lav/Papers/klein_murray_ismar2007/klein_murray_ismar2007.pdf",
      "finalDownloadUrl": "https://www.robots.ox.ac.uk/~lav/Papers/klein_murray_ismar2007/klein_murray_ismar2007.pdf",
      "sha256": "a71a700a0a56b3893915c43f78b741d47fdbe60e1ff58071a11d6881b9b0065f",
      "bytes": 1618643,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:35:45.509195+00:00",
      "publicationDate": "2007",
      "publicationDateSourceUrl": "https://www.robots.ox.ac.uk/~lav/Papers/klein_murray_ismar2007/klein_murray_ismar2007.html",
      "license": "Copyright retained by authors or copyright holders; reposting usually requires permission.",
      "licenseSourceUrl": "https://www.robots.ox.ac.uk/~lav/Papers/klein_murray_ismar2007/klein_murray_ismar2007.html",
      "licenseStatus": "rights_notice_verified",
      "licenseScope": "paper; does not establish code license",
      "pages": 10,
      "sourceIdentityStatus": "title_match_in_pdf",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.557373+00:00"
    },
    {
      "id": "monoslam-2007",
      "originalSourceUrl": "https://www.robots.ox.ac.uk/~lav/Papers/davison_etal_pami2007/davison_etal_pami2007.pdf",
      "finalDownloadUrl": "https://www.robots.ox.ac.uk/~lav/Papers/davison_etal_pami2007/davison_etal_pami2007.pdf",
      "sha256": "a564a4fd07e9a9c52bf0dcf46c30e691367df89b78d351200e16b29508a91e30",
      "bytes": 943903,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T13:35:37.060161+00:00",
      "publicationDate": "2007",
      "publicationDateSourceUrl": "https://www.robots.ox.ac.uk/~lav/Papers/davison_etal_pami2007/davison_etal_pami2007.html",
      "license": "Copyright retained by authors or copyright holders; reposting usually requires permission.",
      "licenseSourceUrl": "https://www.robots.ox.ac.uk/~lav/Papers/davison_etal_pami2007/davison_etal_pami2007.html",
      "licenseStatus": "rights_notice_verified",
      "licenseScope": "paper; does not establish code license",
      "pages": 24,
      "sourceIdentityStatus": "title_match_in_pdf",
      "documentVersion": "Author-hosted manuscript (24 pages)",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T13:45:15.555067+00:00"
    },
    {
      "id": "arxiv-2402.10329",
      "originalSourceUrl": "https://arxiv.org/pdf/2402.10329v3",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2402.10329v3",
      "finalDownloadUrl": "https://arxiv.org/pdf/2402.10329v3",
      "sha256": "a9452cbaf9f5d2a77d5f8b631632fa7f45ae4bbc32400be1cc939b91a36e1609",
      "bytes": 7570839,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T14:59:31.229722+00:00",
      "publicationDate": "2024/02/15",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2402.10329v3",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2402.10329v3",
      "pages": 18,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots",
      "sourceVersion": "2402.10329v3",
      "sourceVersionDate": "2024/03/06",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2402.10329v3",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2402.10329"
    },
    {
      "id": "arxiv-2308.12952",
      "originalSourceUrl": "https://arxiv.org/pdf/2308.12952v3",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2308.12952v3",
      "finalDownloadUrl": "https://arxiv.org/pdf/2308.12952v3",
      "sha256": "aa5fdac48bf9122b22f88150d45575cb0685f2a2f761ca6fc570be743022819b",
      "bytes": 3258884,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T14:59:35.274215+00:00",
      "publicationDate": "2023/08/24",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2308.12952v3",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2308.12952v3",
      "pages": 15,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "BridgeData V2: A Dataset for Robot Learning at Scale",
      "sourceVersion": "2308.12952v3",
      "sourceVersionDate": "2024/01/17",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2308.12952v3",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2308.12952"
    },
    {
      "id": "arxiv-2310.17596",
      "originalSourceUrl": "https://arxiv.org/pdf/2310.17596v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2310.17596v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2310.17596v1",
      "sha256": "7345661fb8e8581981e272e1e043561cbfdaf3f8403d2cb5e28f70797c9bbb16",
      "bytes": 14209120,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T14:59:32.240117+00:00",
      "publicationDate": "2023/10/26",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2310.17596v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2310.17596v1",
      "pages": 45,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations",
      "sourceVersion": "2310.17596v1",
      "sourceVersionDate": "2023/10/26",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2310.17596v1",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2310.17596"
    },
    {
      "id": "arxiv-2302.12422",
      "originalSourceUrl": "https://arxiv.org/pdf/2302.12422v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2302.12422v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2302.12422v2",
      "sha256": "ba6056f66abae90f12c95cc44f9b6714cf6766a6ed7eec6f19766aa0f2685ee5",
      "bytes": 11211178,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:01:25.265828+00:00",
      "publicationDate": "2023/02/24",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2302.12422v2",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2302.12422v2",
      "pages": 21,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "MimicPlay: Long-Horizon Imitation Learning by Watching Human Play",
      "sourceVersion": "2302.12422v2",
      "sourceVersionDate": "2023/10/13",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2302.12422v2",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2302.12422"
    },
    {
      "id": "arxiv-2209.05451",
      "originalSourceUrl": "https://arxiv.org/pdf/2209.05451v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2209.05451v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2209.05451v2",
      "sha256": "daab02c1ba8c47505f9eb54e8e61fd327e799bb20b392efd7f4d06b0357d0f17",
      "bytes": 8181953,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T14:59:39.854116+00:00",
      "publicationDate": "2022/09/12",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2209.05451v2",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2209.05451v2",
      "pages": 28,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation",
      "sourceVersion": "2209.05451v2",
      "sourceVersionDate": "2022/11/11",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2209.05451v2",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2209.05451"
    },
    {
      "id": "arxiv-2306.14896",
      "originalSourceUrl": "https://arxiv.org/pdf/2306.14896v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2306.14896v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2306.14896v1",
      "sha256": "73f97253e2252b274ca6f96a14279685cd7c5068575e3bb3679646d0d71707fe",
      "bytes": 6045133,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:01:25.339834+00:00",
      "publicationDate": "2023/06/26",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2306.14896v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2306.14896v1",
      "pages": 16,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "RVT: Robotic View Transformer for 3D Object Manipulation",
      "sourceVersion": "2306.14896v1",
      "sourceVersionDate": "2023/06/26",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2306.14896v1",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2306.14896"
    },
    {
      "id": "arxiv-2403.03954",
      "originalSourceUrl": "https://arxiv.org/pdf/2403.03954v7",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2403.03954v7",
      "finalDownloadUrl": "https://arxiv.org/pdf/2403.03954v7",
      "sha256": "916ecb6011e5e311daa9a8ca53d0ec2d8f44f7d2034d9ba368de7102737d9682",
      "bytes": 14149153,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T14:59:42.736715+00:00",
      "publicationDate": "2024/03/06",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2403.03954v7",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2403.03954v7",
      "pages": 17,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations",
      "sourceVersion": "2403.03954v7",
      "sourceVersionDate": "2024/09/27",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2403.03954v7",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2403.03954"
    },
    {
      "id": "arxiv-2307.05973",
      "originalSourceUrl": "https://arxiv.org/pdf/2307.05973v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2307.05973v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2307.05973v2",
      "sha256": "cf1cadcf7a1ee44979908c07698f87755c9b5340a79420db509a92d6d2533d42",
      "bytes": 9374922,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T14:59:45.493022+00:00",
      "publicationDate": "2023/07/12",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2307.05973v2",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2307.05973v2",
      "pages": 23,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models",
      "sourceVersion": "2307.05973v2",
      "sourceVersionDate": "2023/11/02",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2307.05973v2",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2307.05973"
    },
    {
      "id": "arxiv-2209.07753",
      "originalSourceUrl": "https://arxiv.org/pdf/2209.07753v4",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2209.07753v4",
      "finalDownloadUrl": "https://arxiv.org/pdf/2209.07753v4",
      "sha256": "e36857fa13746da031444ec59549e61204ca92d599b1d048ac1c55aaf1f6d0a3",
      "bytes": 3200561,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T14:59:50.163040+00:00",
      "publicationDate": "2022/09/16",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2209.07753v4",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2209.07753v4",
      "pages": 16,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Code as Policies: Language Model Programs for Embodied Control",
      "sourceVersion": "2209.07753v4",
      "sourceVersionDate": "2023/05/25",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2209.07753v4",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2209.07753"
    },
    {
      "id": "arxiv-2207.05608",
      "originalSourceUrl": "https://arxiv.org/pdf/2207.05608v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2207.05608v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2207.05608v1",
      "sha256": "ecf30268add2af672291ad65b53c9fd87801f6490b0af195b12db1dedee0f2b9",
      "bytes": 10805774,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T14:59:50.319562+00:00",
      "publicationDate": "2022/07/12",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2207.05608v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2207.05608v1",
      "pages": 25,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Inner Monologue: Embodied Reasoning through Planning with Language Models",
      "sourceVersion": "2207.05608v1",
      "sourceVersionDate": "2022/07/12",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2207.05608v1",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2207.05608"
    },
    {
      "id": "arxiv-1909.12271",
      "originalSourceUrl": "https://arxiv.org/pdf/1909.12271v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1909.12271v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/1909.12271v1",
      "sha256": "fbb04509bea7bf6aa9b97b07c46d95e5c1a900987599693b3fae3fd84377db76",
      "bytes": 3732227,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T14:59:53.906074+00:00",
      "publicationDate": "2019/09/26",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1909.12271v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1909.12271v1",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "RLBench: The Robot Learning Benchmark & Learning Environment",
      "sourceVersion": "1909.12271v1",
      "sourceVersionDate": "2019/09/26",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1909.12271v1",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1909.12271"
    },
    {
      "id": "arxiv-2112.03227",
      "originalSourceUrl": "https://arxiv.org/pdf/2112.03227v4",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2112.03227v4",
      "finalDownloadUrl": "https://arxiv.org/pdf/2112.03227v4",
      "sha256": "c8ad4741782fa8fb773377fbf61b8772b86574f255599a229d3f6ad4d878c60e",
      "bytes": 2092247,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T14:59:56.955250+00:00",
      "publicationDate": "2021/12/06",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2112.03227v4",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2112.03227v4",
      "pages": 10,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks",
      "sourceVersion": "2112.03227v4",
      "sourceVersionDate": "2022/07/13",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2112.03227v4",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2112.03227"
    },
    {
      "id": "arxiv-1910.10897",
      "originalSourceUrl": "https://arxiv.org/pdf/1910.10897v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/1910.10897v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/1910.10897v2",
      "sha256": "8ea4fd9e7a2f7a2cfc475ae7e7021e7a6c03b99ae3932b455def9197ff1197e8",
      "bytes": 6237424,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T14:59:57.241402+00:00",
      "publicationDate": "2019/10/24",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/1910.10897v2",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/1910.10897v2",
      "pages": 40,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning",
      "sourceVersion": "1910.10897v2",
      "sourceVersionDate": "2021/06/14",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/1910.10897v2",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/1910.10897"
    },
    {
      "id": "arxiv-2302.04659",
      "originalSourceUrl": "https://arxiv.org/pdf/2302.04659v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2302.04659v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2302.04659v1",
      "sha256": "89fb794345d860ee696ca2f4d7a75059b15352b615794eeadb0e6075426136f0",
      "bytes": 7635048,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:00:02.866027+00:00",
      "publicationDate": "2023/02/09",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2302.04659v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2302.04659v1",
      "pages": 30,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills",
      "sourceVersion": "2302.04659v1",
      "sourceVersionDate": "2023/02/09",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2302.04659v1",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2302.04659"
    },
    {
      "id": "arxiv-2009.12293",
      "originalSourceUrl": "https://arxiv.org/pdf/2009.12293v3",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2009.12293v3",
      "finalDownloadUrl": "https://arxiv.org/pdf/2009.12293v3",
      "sha256": "3da1cc7ba84ee487a90d7013325dd6045eea7c2920bc50cdb8ff37db67426fd4",
      "bytes": 18253350,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:01:24.788140+00:00",
      "publicationDate": "2020/09/25",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2009.12293v3",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2009.12293v3",
      "pages": 19,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "robosuite: A Modular Simulation Framework and Benchmark for Robot Learning",
      "sourceVersion": "2009.12293v3",
      "sourceVersionDate": "2025/01/18",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2009.12293v3",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2009.12293"
    },
    {
      "id": "arxiv-2106.14405",
      "originalSourceUrl": "https://arxiv.org/pdf/2106.14405v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2106.14405v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2106.14405v2",
      "sha256": "92f9c30479fe4203f656c218fa228c7e5fd71f23a9821b3afa47e06dbe5ab317",
      "bytes": 45408472,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:00:09.985654+00:00",
      "publicationDate": "2021/06/28",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2106.14405v2",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2106.14405v2",
      "pages": 32,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Habitat 2.0: Training Home Assistants to Rearrange their Habitat",
      "sourceVersion": "2106.14405v2",
      "sourceVersionDate": "2022/07/01",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2106.14405v2",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2106.14405"
    },
    {
      "id": "arxiv-2310.13724",
      "originalSourceUrl": "https://arxiv.org/pdf/2310.13724v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2310.13724v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2310.13724v1",
      "sha256": "6383018901acbf7677050585da9a30707437cf7119def797be500f33a68021af",
      "bytes": 8852187,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:00:09.351040+00:00",
      "publicationDate": "2023/10/19",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2310.13724v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2310.13724v1",
      "pages": 30,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots",
      "sourceVersion": "2310.13724v1",
      "sourceVersionDate": "2023/10/19",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2310.13724v1",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2310.13724"
    },
    {
      "id": "arxiv-2403.09227",
      "originalSourceUrl": "https://arxiv.org/pdf/2403.09227v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2403.09227v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2403.09227v1",
      "sha256": "ab4033f3e8a8187ad2cfdf11f1979d33996ecce1e81fa3d62af33a92bbb17a2b",
      "bytes": 14233640,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:00:15.230868+00:00",
      "publicationDate": "2024/03/14",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2403.09227v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2403.09227v1",
      "pages": 43,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation",
      "sourceVersion": "2403.09227v1",
      "sourceVersionDate": "2024/03/14",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2403.09227v1",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2403.09227"
    },
    {
      "id": "arxiv-2210.02697",
      "originalSourceUrl": "https://arxiv.org/pdf/2210.02697v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2210.02697v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2210.02697v2",
      "sha256": "c1b5fe6258e25369626a6ac1df06218394bbb3fb3aa4bb41980dca074e6c04b8",
      "bytes": 4584838,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:00:14.649001+00:00",
      "publicationDate": "2022/10/06",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2210.02697v2",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2210.02697v2",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation",
      "sourceVersion": "2210.02697v2",
      "sourceVersionDate": "2023/03/08",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2210.02697v2",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2210.02697"
    },
    {
      "id": "arxiv-2403.07788",
      "originalSourceUrl": "https://arxiv.org/pdf/2403.07788v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2403.07788v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2403.07788v2",
      "sha256": "ad87015fd70061e5d0b6d4b21c22411c8071328766892a55f133b652d16de87a",
      "bytes": 23271528,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:00:20.780871+00:00",
      "publicationDate": "2024/03/12",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2403.07788v2",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2403.07788v2",
      "pages": 20,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation",
      "sourceVersion": "2403.07788v2",
      "sourceVersionDate": "2024/07/04",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2403.07788v2",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2403.07788"
    },
    {
      "id": "arxiv-2309.05665",
      "originalSourceUrl": "https://arxiv.org/pdf/2309.05665v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2309.05665v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2309.05665v2",
      "sha256": "373da1078eaafff39404d6d3533f8718367ad8b1cca55125128e395692f99b69",
      "bytes": 7511090,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:00:19.923951+00:00",
      "publicationDate": "2023/09/11",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2309.05665v2",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2309.05665v2",
      "pages": 20,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Robot Parkour Learning",
      "sourceVersion": "2309.05665v2",
      "sourceVersionDate": "2023/09/12",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2309.05665v2",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2309.05665"
    },
    {
      "id": "arxiv-2309.14341",
      "originalSourceUrl": "https://arxiv.org/pdf/2309.14341v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2309.14341v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2309.14341v1",
      "sha256": "50f1cf2b73b9147111100994d1dfffbfd15a9a6c2412aee1921d4d3e58ee2285",
      "bytes": 6442374,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:00:27.282739+00:00",
      "publicationDate": "2023/09/25",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2309.14341v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2309.14341v1",
      "pages": 12,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Extreme Parkour with Legged Robots",
      "sourceVersion": "2309.14341v1",
      "sourceVersionDate": "2023/09/25",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2309.14341v1",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2309.14341"
    },
    {
      "id": "arxiv-2301.10602",
      "originalSourceUrl": "https://arxiv.org/pdf/2301.10602v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2301.10602v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2301.10602v2",
      "sha256": "fb02d20879c38b2ca7d0b52ff58174f2119451dea23e946c3eecfccdfcce1cfd",
      "bytes": 2788181,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:00:31.157800+00:00",
      "publicationDate": "2023/01/25",
      "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2301.10602v2",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2301.10602v2",
      "pages": 7,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "DreamWaQ: Learning Robust Quadrupedal Locomotion With Implicit Terrain Imagination via Deep Reinforcement Learning",
      "sourceVersion": "2301.10602v2",
      "sourceVersionDate": "2023/03/03",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2301.10602v2",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2301.10602"
    },
    {
      "id": "arxiv-2409.13678",
      "originalSourceUrl": "https://arxiv.org/pdf/2409.13678v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2409.13678v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2409.13678v1",
      "sha256": "f903a60fc167acc21a4a99dc010bbf51634561ac6a278375001e5548cd0c17bd",
      "bytes": 3718278,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:00:31.106836+00:00",
      "publicationDate": "2024/09/20",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2409.13678v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2409.13678v1",
      "pages": 18,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experience",
      "sourceVersion": "2409.13678v1",
      "sourceVersionDate": "2024/09/20",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2409.13678v1",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2409.13678"
    },
    {
      "id": "arxiv-2108.10869",
      "originalSourceUrl": "https://arxiv.org/pdf/2108.10869v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2108.10869v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2108.10869v2",
      "sha256": "0e15f20bff5f7ceac468c2899baafc8c114a3018c7a7b213eed7c402e5ccec90",
      "bytes": 11003883,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:00:31.058980+00:00",
      "publicationDate": "2021/08/24",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2108.10869v2",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2108.10869v2",
      "pages": 15,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras",
      "sourceVersion": "2108.10869v2",
      "sourceVersionDate": "2022/02/02",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2108.10869v2",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2108.10869"
    },
    {
      "id": "arxiv-2112.12130",
      "originalSourceUrl": "https://arxiv.org/pdf/2112.12130v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2112.12130v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2112.12130v2",
      "sha256": "734cc95a355c07c035696ef7610161522a64af4e9f86d99c2ab3eb1154eb05c6",
      "bytes": 27574309,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:00:38.532507+00:00",
      "publicationDate": "2021/12/22",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2112.12130v2",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2112.12130v2",
      "pages": 17,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "NICE-SLAM: Neural Implicit Scalable Encoding for SLAM",
      "sourceVersion": "2112.12130v2",
      "sourceVersionDate": "2022/04/21",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2112.12130v2",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2112.12130"
    },
    {
      "id": "arxiv-2103.12352",
      "originalSourceUrl": "https://arxiv.org/pdf/2103.12352v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2103.12352v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2103.12352v2",
      "sha256": "bd10370f5fc5eedc1ea3ebc4bd6fd7164164b3b7aad38668035b69b4038f378c",
      "bytes": 8480607,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:00:38.235804+00:00",
      "publicationDate": "2021/03/23",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2103.12352v2",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2103.12352v2",
      "pages": 10,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "iMAP: Implicit Mapping and Positioning in Real-Time",
      "sourceVersion": "2103.12352v2",
      "sourceVersionDate": "2021/09/13",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2103.12352v2",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2103.12352"
    },
    {
      "id": "arxiv-2312.02126",
      "originalSourceUrl": "https://arxiv.org/pdf/2312.02126v3",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2312.02126v3",
      "finalDownloadUrl": "https://arxiv.org/pdf/2312.02126v3",
      "sha256": "c8067647cb2ba3b446017c730dfd39a453570f34e41c5b2b27d2d8a1861830fb",
      "bytes": 11801214,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:00:43.183574+00:00",
      "publicationDate": "2023/12/04",
      "license": "http://creativecommons.org/licenses/by-sa/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2312.02126v3",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2312.02126v3",
      "pages": 11,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM",
      "sourceVersion": "2312.02126v3",
      "sourceVersionDate": "2024/04/16",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2312.02126v3",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2312.02126"
    },
    {
      "id": "arxiv-2408.14035",
      "originalSourceUrl": "https://arxiv.org/pdf/2408.14035v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2408.14035v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2408.14035v2",
      "sha256": "8a9e5643ff99e4d9b735507ddd80fddb6af38401f635d72a0bf017eda57c5695",
      "bytes": 39653122,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:00:43.270255+00:00",
      "publicationDate": "2024/08/26",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2408.14035v2",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2408.14035v2",
      "pages": 30,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry",
      "sourceVersion": "2408.14035v2",
      "sourceVersionDate": "2024/08/28",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2408.14035v2",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2408.14035"
    },
    {
      "id": "arxiv-2312.03275",
      "originalSourceUrl": "https://arxiv.org/pdf/2312.03275v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2312.03275v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2312.03275v1",
      "sha256": "07f1f60fae11be46c488c1fbf5581c8f6d44904ac39ebb6071050d44d731efce",
      "bytes": 1653895,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:01:35.687962+00:00",
      "publicationDate": "2023/12/06",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2312.03275v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2312.03275v1",
      "pages": 7,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation",
      "sourceVersion": "2312.03275v1",
      "sourceVersionDate": "2023/12/06",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2312.03275v1",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2312.03275"
    },
    {
      "id": "arxiv-2207.04429",
      "originalSourceUrl": "https://arxiv.org/pdf/2207.04429v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2207.04429v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2207.04429v2",
      "sha256": "ca454c56aee5ef49666684b7a8daed62233fa12c439656bcd7f6c51265e89ffb",
      "bytes": 4715102,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:00:50.474650+00:00",
      "publicationDate": "2022/07/10",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2207.04429v2",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2207.04429v2",
      "pages": 18,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action",
      "sourceVersion": "2207.04429v2",
      "sourceVersionDate": "2022/07/26",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2207.04429v2",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2207.04429"
    },
    {
      "id": "arxiv-2310.07896",
      "originalSourceUrl": "https://arxiv.org/pdf/2310.07896v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2310.07896v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2310.07896v1",
      "sha256": "05fe73918a7e454c6a006b7cba9aaec6bfc46ce96f65e28eb7a0967263a48af9",
      "bytes": 2364867,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:00:49.728730+00:00",
      "publicationDate": "2023/10/11",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2310.07896v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2310.07896v1",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration",
      "sourceVersion": "2310.07896v1",
      "sourceVersionDate": "2023/10/11",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2310.07896v1",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2310.07896"
    },
    {
      "id": "arxiv-2306.14846",
      "originalSourceUrl": "https://arxiv.org/pdf/2306.14846v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2306.14846v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2306.14846v2",
      "sha256": "175369795be4c276d74c76aa39c4c977b742d994bb717fcdf582052dc311d37d",
      "bytes": 7939854,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:00:53.519926+00:00",
      "publicationDate": "2023/06/26",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2306.14846v2",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2306.14846v2",
      "pages": 25,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "ViNT: A Foundation Model for Visual Navigation",
      "sourceVersion": "2306.14846v2",
      "sourceVersionDate": "2023/10/24",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2306.14846v2",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2306.14846"
    },
    {
      "id": "arxiv-2210.03370",
      "originalSourceUrl": "https://arxiv.org/pdf/2210.03370v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2210.03370v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2210.03370v2",
      "sha256": "18b4f3c35feb35874d6db54d5f3f0eca9535c546877cfa747a3524fc5f841c3a",
      "bytes": 5181975,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:01:35.786862+00:00",
      "publicationDate": "2022/10/07",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2210.03370v2",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2210.03370v2",
      "pages": 8,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "GNM: A General Navigation Model to Drive Any Robot",
      "sourceVersion": "2210.03370v2",
      "sourceVersionDate": "2023/05/22",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2210.03370v2",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2210.03370"
    },
    {
      "id": "arxiv-2302.00111",
      "originalSourceUrl": "https://arxiv.org/pdf/2302.00111v3",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2302.00111v3",
      "finalDownloadUrl": "https://arxiv.org/pdf/2302.00111v3",
      "sha256": "5ded462cfcad30a6317610a4f991d3c1eca7826cbe208dbd9929c3837529708e",
      "bytes": 6171147,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:00:58.877825+00:00",
      "publicationDate": "2023/01/31",
      "license": "http://creativecommons.org/licenses/by/4.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2302.00111v3",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2302.00111v3",
      "pages": 17,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Learning Universal Policies via Text-Guided Video Generation",
      "sourceVersion": "2302.00111v3",
      "sourceVersionDate": "2023/11/20",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2302.00111v3",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2302.00111"
    },
    {
      "id": "arxiv-2310.08576",
      "originalSourceUrl": "https://arxiv.org/pdf/2310.08576v1",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2310.08576v1",
      "finalDownloadUrl": "https://arxiv.org/pdf/2310.08576v1",
      "sha256": "678d6b56c8acf054a0af49c287534c43ad7b0a7ffb3f00153512a1d41b3df540",
      "bytes": 11181162,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:01:05.977138+00:00",
      "publicationDate": "2023/10/12",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2310.08576v1",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2310.08576v1",
      "pages": 19,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Learning to Act from Actionless Videos through Dense Correspondences",
      "sourceVersion": "2310.08576v1",
      "sourceVersionDate": "2023/10/12",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2310.08576v1",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2310.08576"
    },
    {
      "id": "arxiv-2311.01455",
      "originalSourceUrl": "https://arxiv.org/pdf/2311.01455v3",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2311.01455v3",
      "finalDownloadUrl": "https://arxiv.org/pdf/2311.01455v3",
      "sha256": "4146b2443205d6e4f8137e14fb20a91165da9a70c12306a300bc71fcae53b022",
      "bytes": 34123085,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:01:12.102944+00:00",
      "publicationDate": "2023/11/02",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2311.01455v3",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2311.01455v3",
      "pages": 48,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation",
      "sourceVersion": "2311.01455v3",
      "sourceVersionDate": "2024/06/14",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2311.01455v3",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2311.01455"
    },
    {
      "id": "arxiv-2205.09991",
      "originalSourceUrl": "https://arxiv.org/pdf/2205.09991v2",
      "versionedOriginalUrl": "https://arxiv.org/pdf/2205.09991v2",
      "finalDownloadUrl": "https://arxiv.org/pdf/2205.09991v2",
      "sha256": "aafe149adb5476e8b8b061c02d26824c42fb14a71ce8ae37b1a0e375452d7a1f",
      "bytes": 10498721,
      "downloadStatus": "downloaded",
      "retrievedAt": "2026-10-04T15:01:10.785629+00:00",
      "publicationDate": "2022/05/20",
      "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
      "licenseSourceUrl": "https://arxiv.org/abs/2205.09991v2",
      "licenseStatus": "license_url_verified",
      "licenseScope": "paper; does not establish code license",
      "metadataStatus": "checked",
      "metadataSourceUrl": "https://arxiv.org/abs/2205.09991v2",
      "pages": 14,
      "sourceIdentityStatus": "title_match",
      "sourceTitle": "Planning with Diffusion for Flexible Behavior Synthesis",
      "sourceVersion": "2205.09991v2",
      "sourceVersionDate": "2022/12/21",
      "archiveValidationStatus": "validated",
      "archiveValidatedAt": "2026-10-04T15:21:15.250223+00:00",
      "publicationDateSourceUrl": "https://arxiv.org/abs/2205.09991v2",
      "unversionedOriginalSourceUrl": "https://arxiv.org/pdf/2205.09991"
    }
  ]
}