{ "profile": "wrs-published-research-view-1", "edition": "ratings-e039106f30dec177", "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS", "entry": { "id": "brohan-et-al-rt2-2023", "title": "Brohan and colleagues: RT-2 vision-language-action robotic control", "summary": "Co-fine-tuned vision-language models on web data and robot trajectories while representing robot actions as tokens, reporting transfer to new robotic tasks.", "boundary": "RT-2 results concern the studied robots, tasks and setups; they do not prove general-purpose real-world robotic reasoning.", "area": "Vision-language-action robotics", "topic": "Artificial intelligence", "year": 2023, "lane": "HUMAN", "result": "ALGORITHM", "package_id": "brohan-et-al-rt2-2023", "target": { "record_id": "urn:uuid:a3323595-8cc7-4928-a537-641c05920af3", "version": 1, "content_hash": "sha256:8ce64b1d83fb83760150f256b4f4ca795a8dbd03d2f1a6d03a58d6c5761e054f" }, "humans": [ "Anthony Brohan", "Noah Brown", "Justice Carbajal", "Yevgen Chebotar", "Xi Chen", "Krzysztof Choromanski", "Tianli Ding", "Danny Driess", "Avinava Dubey", "Chelsea Finn", "Pete Florence", "Chuyuan Fu", "Montse Gonzalez Arenas", "Keerthana Gopalakrishnan", "Kehang Han", "Karol Hausman", "Alexander Herzog", "Jasmine Hsu", "Brian Ichter", "Alex Irpan", "Nikhil Joshi", "Ryan Julian", "Dmitry Kalashnikov", "Yuheng Kuang", "Isabel Leal", "Lisa Lee", "Tsang-Wei Edward Lee", "Sergey Levine", "Yao Lu", "Henryk Michalewski", "Igor Mordatch", "Karl Pertsch", "Kanishka Rao", "Krista Reymann", "Michael Ryoo", "Grecia Salazar", "Pannag Sanketi", "Pierre Sermanet", "Jaspiar Singh", "Anikait Singh", "Radu Soricut", "Huong Tran", "Vincent Vanhoucke", "Quan Vuong", "Ayzaan Wahid", "Stefan Welker", "Paul Wohlhart", "Jialin Wu", "Fei Xia", "Ted Xiao", "Peng Xu", "Sichun Xu", "Tianhe Yu", "Brianna Zitkovich" ], "authors_complete": true, "human_role_note": "Complete named paper byline. Human research, source-reported system execution and experimental validation are distinct; individual effort shares are not measured.", "agents": [], "related": [], "subresults": [], "scientific_assessment": { "source_review": "SOURCE_CURATED", "scientific_review": "NOT_REVIEWED_BY_WRS", "formal_replay": "NOT_RUN", "provider_attestation": "NONE" }, "sources": [ { "id": "arxiv-2307-15818", "title": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" }, { "id": "company-brohan-et-al-rt2-2023", "title": "Brohan and colleagues: RT-2 vision-language-action robotic control — official research page", "url": "https://deepmind.google/blog/rt-2-new-model-translates-vision-and-language-into-action/" } ], "points": "28000", "published_grade": { "id": "brohan-et-al-rt2-2023", "entry_id": "brohan-et-al-rt2-2023", "band": "B", "modifier": null, "target": { "record_id": "urn:uuid:a3323595-8cc7-4928-a537-641c05920af3", "version": 1, "content_hash": "sha256:8ce64b1d83fb83760150f256b4f4ca795a8dbd03d2f1a6d03a58d6c5761e054f" }, "what_changed": "Co-fine-tuned vision-language models on web data and robot trajectories while representing robot actions as tokens, reporting transfer to new robotic tasks.", "scope": "Co-fine-tuned vision-language models on web data and robot trajectories while representing robot actions as tokens, reporting transfer to new robotic tasks. Scope limitation: RT-2 results concern the studied robots, tasks and setups; they do not prove general-purpose real-world robotic reasoning.", "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:a3323595-8cc7-4928-a537-641c05920af3", "version": 1, "content_hash": "sha256:8ce64b1d83fb83760150f256b4f4ca795a8dbd03d2f1a6d03a58d6c5761e054f" }, "edition": "ratings-e039106f30dec177" } }, "version": { "kind": "PUBLIC_RECORD_VIEW", "previous": null, "published_at": "2026-09-27T00:00:00Z", "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": "Anthony Brohan", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Noah Brown", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Justice Carbajal", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yevgen Chebotar", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Xi Chen", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Krzysztof Choromanski", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Tianli Ding", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Danny Driess", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Avinava Dubey", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Chelsea Finn", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Pete Florence", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Chuyuan Fu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Montse Gonzalez Arenas", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Keerthana Gopalakrishnan", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Kehang Han", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Karol Hausman", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Alexander Herzog", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Jasmine Hsu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Brian Ichter", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Alex Irpan", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Nikhil Joshi", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ryan Julian", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Dmitry Kalashnikov", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yuheng Kuang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Isabel Leal", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Lisa Lee", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Tsang-Wei Edward Lee", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Sergey Levine", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yao Lu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Henryk Michalewski", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Igor Mordatch", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } } ], "evidence": [ { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-0", "kind": "source_reference", "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" } }, { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-1", "kind": "source_reference", "source": { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — official research page", "url": "https://deepmind.google/blog/rt-2-new-model-translates-vision-and-language-into-action/" } } ], "origin": "HUMAN_LEGACY", "record_profile": "wrs-local-research-notes-0.1", "record_type": "research_note", "rrp_version": "0.1", "scope": { "description": "RT-2 results concern the studied robots, tasks and setups; they do not prove general-purpose real-world robotic reasoning.", "domain": "Vision-language-action robotics" }, "sources": [ { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1" }, { "citation": "Brohan and colleagues: RT-2 vision-language-action robotic control — official research page", "url": "https://deepmind.google/blog/rt-2-new-model-translates-vision-and-language-into-action/" } ], "statement": "# Brohan and colleagues: RT-2 vision-language-action robotic control\n\nCo-fine-tuned vision-language models on web data and robot trajectories while representing robot actions as tokens, reporting transfer to new robotic tasks.\n\n## Scientific scope\n\nRT-2 results concern the studied robots, tasks and setups; they do not prove general-purpose real-world robotic reasoning.\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\nAnthony Brohan; Noah Brown; Justice Carbajal; Yevgen Chebotar; Xi Chen; Krzysztof Choromanski; Tianli Ding; Danny Driess; Avinava Dubey; Chelsea Finn; Pete Florence; Chuyuan Fu; Montse Gonzalez Arenas; Keerthana Gopalakrishnan; Kehang Han; Karol Hausman; Alexander Herzog; Jasmine Hsu; Brian Ichter; Alex Irpan; Nikhil Joshi; Ryan Julian; Dmitry Kalashnikov; Yuheng Kuang; Isabel Leal; Lisa Lee; Tsang-Wei Edward Lee; Sergey Levine; Yao Lu; Henryk Michalewski; Igor Mordatch; Karl Pertsch; Kanishka Rao; Krista Reymann; Michael Ryoo; Grecia Salazar; Pannag Sanketi; Pierre Sermanet; Jaspiar Singh; Anikait Singh; Radu Soricut; Huong Tran; Vincent Vanhoucke; Quan Vuong; Ayzaan Wahid; Stefan Welker; Paul Wohlhart; Jialin Wu; Fei Xia; Ted Xiao; Peng Xu; Sichun Xu; Tianhe Yu; Brianna Zitkovich\n\nComplete named paper byline. Human research, source-reported system execution and experimental validation are distinct; individual effort shares are not measured.\n\n\n\n## Original sources\n\n- [Brohan and colleagues: RT-2 vision-language-action robotic control — original paper](https://arxiv.org/abs/2307.15818v1)\n- [Brohan and colleagues: RT-2 vision-language-action robotic control — official research page](https://deepmind.google/blog/rt-2-new-model-translates-vision-and-language-into-action/)\n", "summary": "Co-fine-tuned vision-language models on web data and robot trajectories while representing robot actions as tokens, reporting transfer to new robotic tasks.", "title": "Brohan and colleagues: RT-2 vision-language-action robotic control" }, "record_id": "urn:uuid:a3323595-8cc7-4928-a537-641c05920af3", "version": 1, "source_ref": { "record_id": "urn:uuid:a3323595-8cc7-4928-a537-641c05920af3", "version": 1, "content_hash": "sha256:8ce64b1d83fb83760150f256b4f4ca795a8dbd03d2f1a6d03a58d6c5761e054f" }, "export_view": "wrs-public-editorial-view-1", "public_view_hash": "sha256:f71e4aa6783b33bc0cb78e649dd3cafdf5895cc3bbabbcd4efd9cb0b808cefb5" }, "target": { "record_id": "urn:uuid:a3323595-8cc7-4928-a537-641c05920af3", "version": 1, "content_hash": "sha256:8ce64b1d83fb83760150f256b4f4ca795a8dbd03d2f1a6d03a58d6c5761e054f" }, "published_grade": { "profile": "wrs-published-grade-1", "edition": "2026-10-28.1", "id": "brohan-et-al-rt2-2023", "entry_id": "brohan-et-al-rt2-2023", "revision": 1, "title": "Brohan and colleagues: RT-2 vision-language-action robotic control", "context": "Vision-language-action robotics", "track": "Human-designed AI research method or resource", "band": "B", "modifier": null, "status": "PROVISIONAL_EDITORIAL", "assessed_on": "2026-09-27", "evidence_cutoff": "2026-09-27", "achievement_state": "SUPPORTED_SCOPED_RESULT", "what_changed": "Co-fine-tuned vision-language models on web data and robot trajectories while representing robot actions as tokens, reporting transfer to new robotic tasks.", "scope": "Co-fine-tuned vision-language models on web data and robot trajectories while representing robot actions as tokens, reporting transfer to new robotic tasks. Scope limitation: RT-2 results concern the studied robots, tasks and setups; they do not prove general-purpose real-world robotic reasoning.", "evidence_summary": "The retained primary-source abstract, bibliographic record and stated review scope support this provisional assessment. No independent experimental replication by WRS is claimed. RT-2 results concern the studied robots, tasks and setups; they do not prove general-purpose real-world robotic reasoning.", "references": [ { "title": "Brohan and colleagues: RT-2 vision-language-action robotic control — original paper", "url": "https://arxiv.org/abs/2307.15818v1", "locator": "Abstract and complete bibliographic byline for 2307.15818v1; not an independent proof or experimental replication." }, { "title": "Brohan and colleagues: RT-2 vision-language-action robotic control — official research page", "url": "https://deepmind.google/blog/rt-2-new-model-translates-vision-and-language-into-action/", "locator": "Source-linked contribution and stated scientific limits; not an independent replication." } ], "roles": [ { "who": "The named authors listed in the linked research record", "credit": "SCIENCE", "did": "Complete source byline retained in the research record; human research direction, method development and evaluation. Individual labor shares are not measured." } ], "target": { "record_id": "urn:uuid:a3323595-8cc7-4928-a537-641c05920af3", "version": 1, "content_hash": "sha256:8ce64b1d83fb83760150f256b4f4ca795a8dbd03d2f1a6d03a58d6c5761e054f" }, "scientific_correctness_certified": false, "independent_expert_calibration": false, "method": "PROPRIETARY", "points": "28000" }, "canonical_agent_submission": false, "scientific_verification_awarded": false, "reader_guide": null, "reading_status": "SOURCE_LINKED_NOTE" }