{ "profile": "wrs-published-research-view-1", "edition": "ratings-e039106f30dec177", "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS", "entry": { "id": "kim-et-al-openvla-research-resource-2024", "title": "Kim et al.: open vision-language-action training and adaptation resource", "summary": "Released a multi-robot vision-language-action model and training pipeline combining fused pretrained visual features, a language backbone and tokenized robot actions, with efficient target-robot fine-tuning.", "boundary": "Prismatic, Llama2, DINOv2, SigLIP and OpenX data are inherited. This is an accessible integrated system/resource, not invention of VLA or LoRA. Selected task success does not certify safe unattended control or universal generalization.", "area": "Open robot foundation-model resources", "topic": "Artificial intelligence", "year": 2024, "lane": "HUMAN", "result": "EMPIRICAL", "package_id": "kim-et-al-openvla-research-resource-2024", "target": { "record_id": "urn:uuid:5e6868b5-b7c9-4e30-a154-6d621eb57f21", "version": 1, "content_hash": "sha256:47a4e2754df296cce789d89d3be994e5be84ae717351814b195dfa76a1e5bc73" }, "humans": [ "Moo Jin Kim", "Karl Pertsch", "Siddharth Karamcheti", "Ted Xiao", "Ashwin Balakrishna", "Suraj Nair", "Rafael Rafailov", "Ethan Foster", "Grace Lam", "Pannag Sanketi", "Quan Vuong", "Thomas Kollar", "Benjamin Burchfiel", "Russ Tedrake", "Dorsa Sadigh", "Sergey Levine", "Percy Liang", "Chelsea Finn" ], "authors_complete": true, "human_role_note": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.", "agents": [], "related": [], "subresults": [], "scientific_assessment": { "source_review": "SOURCE_CURATED", "scientific_review": "NOT_REVIEWED_BY_WRS", "formal_replay": "NOT_RUN", "provider_attestation": "NONE" }, "sources": [ { "id": "cur20261015-arxiv-2406-09246v1", "title": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" }, { "id": "cur20261015-support-kim-et-al-openvla-research-resource-2024", "title": "Kim et al.: open vision-language-action training and adaptation resource — original project", "url": "https://openvla.github.io/" } ], "points": "130000", "published_grade": { "id": "kim-et-al-openvla-research-resource-2024", "entry_id": "kim-et-al-openvla-research-resource-2024", "band": "A", "modifier": null, "target": { "record_id": "urn:uuid:5e6868b5-b7c9-4e30-a154-6d621eb57f21", "version": 1, "content_hash": "sha256:47a4e2754df296cce789d89d3be994e5be84ae717351814b195dfa76a1e5bc73" }, "what_changed": "Released a multi-robot vision-language-action model and training pipeline combining fused pretrained visual features, a language backbone and tokenized robot actions, with efficient target-robot fine-tuning.", "scope": "Released a multi-robot vision-language-action model and training pipeline combining fused pretrained visual features, a language backbone and tokenized robot actions, with efficient target-robot fine-tuning. Prismatic, Llama2, DINOv2, SigLIP and OpenX data are inherited. This is an accessible integrated system/resource, not invention of VLA or LoRA. Selected task success does not certify safe unattended control or universal generalization.", "status": "PROVISIONAL_EDITORIAL", "scientific_correctness_certified": false }, "assessment_disposition": { "status": "ASSESSED", "label": "Provisionally assessed", "reason": "A current grade and separate reference score identify this exact contribution.", "target": { "record_id": "urn:uuid:5e6868b5-b7c9-4e30-a154-6d621eb57f21", "version": 1, "content_hash": "sha256:47a4e2754df296cce789d89d3be994e5be84ae717351814b195dfa76a1e5bc73" }, "edition": "ratings-e039106f30dec177" } }, "version": { "kind": "PUBLIC_RECORD_VIEW", "previous": null, "published_at": "2026-10-16T00:00:00Z", "publisher": { "principal_id": "urn:uuid:80116931-785b-40a2-a24b-9d59db0c7e33", "role": "WRS_EDITORIAL_PUBLICATION" }, "record": { "contributors": [ { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Moo Jin Kim", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Karl Pertsch", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Siddharth Karamcheti", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ted Xiao", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ashwin Balakrishna", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Suraj Nair", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Rafael Rafailov", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ethan Foster", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Grace Lam", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Pannag Sanketi", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Quan Vuong", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Thomas Kollar", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Benjamin Burchfiel", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Russ Tedrake", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Dorsa Sadigh", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Sergey Levine", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Percy Liang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Chelsea Finn", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" } } ], "evidence": [ { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-0", "kind": "source_reference", "source": { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" } }, { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-1", "kind": "source_reference", "source": { "citation": "Kim et al.: open vision-language-action training and adaptation resource — original project", "url": "https://openvla.github.io/" } } ], "origin": "HUMAN_LEGACY", "record_profile": "wrs-local-research-notes-0.1", "record_type": "research_note", "rrp_version": "0.1", "scope": { "description": "Prismatic, Llama2, DINOv2, SigLIP and OpenX data are inherited. This is an accessible integrated system/resource, not invention of VLA or LoRA. Selected task success does not certify safe unattended control or universal generalization.", "domain": "Open robot foundation-model resources" }, "sources": [ { "citation": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1" }, { "citation": "Kim et al.: open vision-language-action training and adaptation resource — original project", "url": "https://openvla.github.io/" } ], "statement": "# Kim et al.: open vision-language-action training and adaptation resource\n\nReleased a multi-robot vision-language-action model and training pipeline combining fused pretrained visual features, a language backbone and tokenized robot actions, with efficient target-robot fine-tuning.\n\n## Scientific scope\n\nPrismatic, Llama2, DINOv2, SigLIP and OpenX data are inherited. This is an accessible integrated system/resource, not invention of VLA or LoRA. Selected task success does not certify safe unattended control or universal generalization.\n\n## Reading status\n\nThis is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.\n\n## People and systems\n\nMoo Jin Kim; Karl Pertsch; Siddharth Karamcheti; Ted Xiao; Ashwin Balakrishna; Suraj Nair; Rafael Rafailov; Ethan Foster; Grace Lam; Pannag Sanketi; Quan Vuong; Thomas Kollar; Benjamin Burchfiel; Russ Tedrake; Dorsa Sadigh; Sergey Levine; Percy Liang; Chelsea Finn\n\nSource-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.\n\n\n\n## Original sources\n\n- [OpenVLA: An Open-Source Vision-Language-Action Model](https://arxiv.org/abs/2406.09246v1)\n- [Kim et al.: open vision-language-action training and adaptation resource — original project](https://openvla.github.io/)\n", "summary": "Released a multi-robot vision-language-action model and training pipeline combining fused pretrained visual features, a language backbone and tokenized robot actions, with efficient target-robot fine-tuning.", "title": "Kim et al.: open vision-language-action training and adaptation resource" }, "record_id": "urn:uuid:5e6868b5-b7c9-4e30-a154-6d621eb57f21", "version": 1, "source_ref": { "record_id": "urn:uuid:5e6868b5-b7c9-4e30-a154-6d621eb57f21", "version": 1, "content_hash": "sha256:47a4e2754df296cce789d89d3be994e5be84ae717351814b195dfa76a1e5bc73" }, "export_view": "wrs-public-editorial-view-1", "public_view_hash": "sha256:70a096b6e1087efff9be58359e7c8704214f744a36a63b37405cf09d786ec24f" }, "target": { "record_id": "urn:uuid:5e6868b5-b7c9-4e30-a154-6d621eb57f21", "version": 1, "content_hash": "sha256:47a4e2754df296cce789d89d3be994e5be84ae717351814b195dfa76a1e5bc73" }, "published_grade": { "profile": "wrs-published-grade-1", "edition": "2026-10-28.1", "id": "kim-et-al-openvla-research-resource-2024", "entry_id": "kim-et-al-openvla-research-resource-2024", "revision": 1, "title": "Kim et al.: open vision-language-action training and adaptation resource", "context": "Open robot foundation-model resources", "track": "Human-designed research method or resource", "band": "A", "modifier": null, "status": "PROVISIONAL_EDITORIAL", "assessed_on": "2026-10-16", "evidence_cutoff": "2026-10-16", "achievement_state": "SUPPORTED_SCOPED_RESULT", "what_changed": "Released a multi-robot vision-language-action model and training pipeline combining fused pretrained visual features, a language backbone and tokenized robot actions, with efficient target-robot fine-tuning.", "scope": "Released a multi-robot vision-language-action model and training pipeline combining fused pretrained visual features, a language backbone and tokenized robot actions, with efficient target-robot fine-tuning. Prismatic, Llama2, DINOv2, SigLIP and OpenX data are inherited. This is an accessible integrated system/resource, not invention of VLA or LoRA. Selected task success does not certify safe unattended control or universal generalization.", "evidence_summary": "The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Prismatic, Llama2, DINOv2, SigLIP and OpenX data are inherited. This is an accessible integrated system/resource, not invention of VLA or LoRA. Selected task success does not certify safe unattended control or universal generalization.", "references": [ { "title": "OpenVLA: An Open-Source Vision-Language-Action Model", "url": "https://arxiv.org/abs/2406.09246v1", "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification." }, { "title": "Kim et al.: open vision-language-action training and adaptation resource — original project", "url": "https://openvla.github.io/", "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification." } ], "roles": [ { "who": "Source-listed authors and technical contributors", "credit": "SCIENCE", "did": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities." } ], "target": { "record_id": "urn:uuid:5e6868b5-b7c9-4e30-a154-6d621eb57f21", "version": 1, "content_hash": "sha256:47a4e2754df296cce789d89d3be994e5be84ae717351814b195dfa76a1e5bc73" }, "scientific_correctness_certified": false, "independent_expert_calibration": false, "method": "PROPRIETARY", "points": "130000" }, "canonical_agent_submission": false, "scientific_verification_awarded": false, "reader_guide": null, "reading_status": "SOURCE_LINKED_NOTE" }