{ "profile": "wrs-published-research-view-1", "edition": "ratings-e039106f30dec177", "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS", "entry": { "id": "assran-et-al-vjepa2-planning-2025", "title": "Assran et al.: V-JEPA 2 video prediction and robot planning", "summary": "Combined self-supervised video representation prediction with action-conditioned post-training on robot trajectories, enabling image-goal planning experiments on robot arms without local task-specific training.", "boundary": "Zero-shot means no additional data from the tested robot environments, not no robot training data. Results are specific tabletop planning tasks, not general physical understanding or safety.", "area": "Audio modeling, latent dynamics and learning feedback", "topic": "Artificial intelligence", "year": 2025, "lane": "HUMAN", "result": "EMPIRICAL", "package_id": "assran-et-al-vjepa2-planning-2025", "target": { "record_id": "urn:uuid:6de558e8-aa2a-4a22-ab46-d7f0fa4de816", "version": 1, "content_hash": "sha256:9e47752f92428b08d1cbe6ebe7dc50057e9ac54bcc6248ba4eede6aa9eefc41d" }, "humans": [ "Mahmoud Assran", "Adrien Bardes", "David Fan", "Quentin Garrido", "Russell Howes", "Mojtaba Komeili", "Matthew Muckley", "Ammar Rizvi", "Claire Roberts", "Koustuv Sinha", "Artem Zholus", "Sergio Arnaud", "Abha Gejji", "Ada Martin", "Francois Robert Hogan", "Daniel Dugas", "Piotr Bojanowski", "Vasil Khalidov", "Patrick Labatut", "Francisco Massa", "Marc Szafraniec", "Kapil Krishnakumar", "Yong Li", "Xiaodong Ma", "Sarath Chandar", "Franziska Meier", "Yann LeCun", "Michael Rabbat", "Nicolas Ballas" ], "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-2506-09985v1", "title": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" }, { "id": "cur20261015-support-assran-et-al-vjepa2-planning-2025", "title": "Assran et al.: V-JEPA 2 video prediction and robot planning — author/company project record", "url": "https://ai.meta.com/research/publications/v-jepa-2-self-supervised-video-models-enable-understanding-prediction-and-planning/" } ], "points": "85000", "published_grade": { "id": "assran-et-al-vjepa2-planning-2025", "entry_id": "assran-et-al-vjepa2-planning-2025", "band": "B", "modifier": "+", "target": { "record_id": "urn:uuid:6de558e8-aa2a-4a22-ab46-d7f0fa4de816", "version": 1, "content_hash": "sha256:9e47752f92428b08d1cbe6ebe7dc50057e9ac54bcc6248ba4eede6aa9eefc41d" }, "what_changed": "Combined self-supervised video representation prediction with action-conditioned post-training on robot trajectories, enabling image-goal planning experiments on robot arms without local task-specific training.", "scope": "Combined self-supervised video representation prediction with action-conditioned post-training on robot trajectories, enabling image-goal planning experiments on robot arms without local task-specific training. Zero-shot means no additional data from the tested robot environments, not no robot training data. Results are specific tabletop planning tasks, not general physical understanding or safety.", "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:6de558e8-aa2a-4a22-ab46-d7f0fa4de816", "version": 1, "content_hash": "sha256:9e47752f92428b08d1cbe6ebe7dc50057e9ac54bcc6248ba4eede6aa9eefc41d" }, "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": "Mahmoud Assran", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Adrien Bardes", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "David Fan", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Quentin Garrido", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Russell Howes", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Mojtaba Komeili", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Matthew Muckley", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ammar Rizvi", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Claire Roberts", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Koustuv Sinha", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Artem Zholus", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Sergio Arnaud", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Abha Gejji", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ada Martin", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Francois Robert Hogan", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Daniel Dugas", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Piotr Bojanowski", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Vasil Khalidov", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Patrick Labatut", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Francisco Massa", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Marc Szafraniec", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Kapil Krishnakumar", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yong Li", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Xiaodong Ma", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Sarath Chandar", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Franziska Meier", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yann LeCun", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Michael Rabbat", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Nicolas Ballas", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } } ], "evidence": [ { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-0", "kind": "source_reference", "source": { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" } }, { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-1", "kind": "source_reference", "source": { "citation": "Assran et al.: V-JEPA 2 video prediction and robot planning — author/company project record", "url": "https://ai.meta.com/research/publications/v-jepa-2-self-supervised-video-models-enable-understanding-prediction-and-planning/" } } ], "origin": "HUMAN_LEGACY", "record_profile": "wrs-local-research-notes-0.1", "record_type": "research_note", "rrp_version": "0.1", "scope": { "description": "Zero-shot means no additional data from the tested robot environments, not no robot training data. Results are specific tabletop planning tasks, not general physical understanding or safety.", "domain": "Audio modeling, latent dynamics and learning feedback" }, "sources": [ { "citation": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1" }, { "citation": "Assran et al.: V-JEPA 2 video prediction and robot planning — author/company project record", "url": "https://ai.meta.com/research/publications/v-jepa-2-self-supervised-video-models-enable-understanding-prediction-and-planning/" } ], "statement": "# Assran et al.: V-JEPA 2 video prediction and robot planning\n\nCombined self-supervised video representation prediction with action-conditioned post-training on robot trajectories, enabling image-goal planning experiments on robot arms without local task-specific training.\n\n## Scientific scope\n\nZero-shot means no additional data from the tested robot environments, not no robot training data. Results are specific tabletop planning tasks, not general physical understanding or safety.\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\nMahmoud Assran; Adrien Bardes; David Fan; Quentin Garrido; Russell Howes; Mojtaba Komeili; Matthew Muckley; Ammar Rizvi; Claire Roberts; Koustuv Sinha; Artem Zholus; Sergio Arnaud; Abha Gejji; Ada Martin; Francois Robert Hogan; Daniel Dugas; Piotr Bojanowski; Vasil Khalidov; Patrick Labatut; Francisco Massa; Marc Szafraniec; Kapil Krishnakumar; Yong Li; Xiaodong Ma; Sarath Chandar; Franziska Meier; Yann LeCun; Michael Rabbat; Nicolas Ballas\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- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://arxiv.org/abs/2506.09985v1)\n- [Assran et al.: V-JEPA 2 video prediction and robot planning — author/company project record](https://ai.meta.com/research/publications/v-jepa-2-self-supervised-video-models-enable-understanding-prediction-and-planning/)\n", "summary": "Combined self-supervised video representation prediction with action-conditioned post-training on robot trajectories, enabling image-goal planning experiments on robot arms without local task-specific training.", "title": "Assran et al.: V-JEPA 2 video prediction and robot planning" }, "record_id": "urn:uuid:6de558e8-aa2a-4a22-ab46-d7f0fa4de816", "version": 1, "source_ref": { "record_id": "urn:uuid:6de558e8-aa2a-4a22-ab46-d7f0fa4de816", "version": 1, "content_hash": "sha256:9e47752f92428b08d1cbe6ebe7dc50057e9ac54bcc6248ba4eede6aa9eefc41d" }, "export_view": "wrs-public-editorial-view-1", "public_view_hash": "sha256:3c9607389ddb215c3751622d7862ee97346a7ec25ea28710ca7207f9c6aca69b" }, "target": { "record_id": "urn:uuid:6de558e8-aa2a-4a22-ab46-d7f0fa4de816", "version": 1, "content_hash": "sha256:9e47752f92428b08d1cbe6ebe7dc50057e9ac54bcc6248ba4eede6aa9eefc41d" }, "published_grade": { "profile": "wrs-published-grade-1", "edition": "2026-10-28.1", "id": "assran-et-al-vjepa2-planning-2025", "entry_id": "assran-et-al-vjepa2-planning-2025", "revision": 1, "title": "Assran et al.: V-JEPA 2 video prediction and robot planning", "context": "Audio modeling, latent dynamics and learning feedback", "track": "Human-designed research method or resource", "band": "B", "modifier": "+", "status": "PROVISIONAL_EDITORIAL", "assessed_on": "2026-10-16", "evidence_cutoff": "2026-10-16", "achievement_state": "SUPPORTED_SCOPED_RESULT", "what_changed": "Combined self-supervised video representation prediction with action-conditioned post-training on robot trajectories, enabling image-goal planning experiments on robot arms without local task-specific training.", "scope": "Combined self-supervised video representation prediction with action-conditioned post-training on robot trajectories, enabling image-goal planning experiments on robot arms without local task-specific training. Zero-shot means no additional data from the tested robot environments, not no robot training data. Results are specific tabletop planning tasks, not general physical understanding or safety.", "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. Zero-shot means no additional data from the tested robot environments, not no robot training data. Results are specific tabletop planning tasks, not general physical understanding or safety.", "references": [ { "title": "V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning", "url": "https://arxiv.org/abs/2506.09985v1", "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification." }, { "title": "Assran et al.: V-JEPA 2 video prediction and robot planning — author/company project record", "url": "https://ai.meta.com/research/publications/v-jepa-2-self-supervised-video-models-enable-understanding-prediction-and-planning/", "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:6de558e8-aa2a-4a22-ab46-d7f0fa4de816", "version": 1, "content_hash": "sha256:9e47752f92428b08d1cbe6ebe7dc50057e9ac54bcc6248ba4eede6aa9eefc41d" }, "scientific_correctness_certified": false, "independent_expert_calibration": false, "method": "PROPRIETARY", "points": "85000" }, "canonical_agent_submission": false, "scientific_verification_awarded": false, "reader_guide": null, "reading_status": "SOURCE_LINKED_NOTE" }