{ "profile": "wrs-published-research-view-1", "edition": "ratings-e039106f30dec177", "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS", "entry": { "id": "kondratyuk-et-al-videopoet-token-generation-2023", "title": "Kondratyuk et al.: autoregressive multimodal video/audio generation", "summary": "Trained a decoder-only transformer on mixed multimodal generation objectives over video, image, text and audio representations, then adapted the pretrained model to conditioned video-generation tasks.", "boundary": "Autoregressive transformers and pretrained tokenizers are inherited. Acquired delta is unified multimodal training/task integration, not generic next-token modeling. Zero-shot generation in tested settings is not arbitrary-domain or long-horizon consistency.", "area": "Multimodal sequence-generation systems", "topic": "Artificial intelligence", "year": 2023, "lane": "HUMAN", "result": "EMPIRICAL", "package_id": "kondratyuk-et-al-videopoet-token-generation-2023", "target": { "record_id": "urn:uuid:5320e429-4c97-4b54-a5b8-2eeb1633d06d", "version": 1, "content_hash": "sha256:bc750a800a8b7f0bc3b86ba9404fda69d3d19a1a8deadd84a9ace1537940f6af" }, "humans": [ "Dan Kondratyuk", "Lijun Yu", "Xiuye Gu", "José Lezama", "Jonathan Huang", "Rachel Hornung", "Hartwig Adam", "Hassan Akbari", "Yair Alon", "Vighnesh Birodkar", "Yong Cheng", "Ming-Chang Chiu", "Josh Dillon", "Irfan Essa", "Agrim Gupta", "Meera Hahn", "Anja Hauth", "David Hendon", "Alonso Martinez", "David Minnen", "David Ross", "Grant Schindler", "Mikhail Sirotenko", "Kihyuk Sohn", "Krishna Somandepalli", "Huisheng Wang", "Jimmy Yan", "Ming-Hsuan Yang", "Xuan Yang", "Bryan Seybold", "Lu Jiang" ], "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-2312-14125v1", "title": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } ], "points": "80000", "published_grade": { "id": "kondratyuk-et-al-videopoet-token-generation-2023", "entry_id": "kondratyuk-et-al-videopoet-token-generation-2023", "band": "B", "modifier": "+", "target": { "record_id": "urn:uuid:5320e429-4c97-4b54-a5b8-2eeb1633d06d", "version": 1, "content_hash": "sha256:bc750a800a8b7f0bc3b86ba9404fda69d3d19a1a8deadd84a9ace1537940f6af" }, "what_changed": "Trained a decoder-only transformer on mixed multimodal generation objectives over video, image, text and audio representations, then adapted the pretrained model to conditioned video-generation tasks.", "scope": "Trained a decoder-only transformer on mixed multimodal generation objectives over video, image, text and audio representations, then adapted the pretrained model to conditioned video-generation tasks. Autoregressive transformers and pretrained tokenizers are inherited. Acquired delta is unified multimodal training/task integration, not generic next-token modeling. Zero-shot generation in tested settings is not arbitrary-domain or long-horizon consistency.", "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:5320e429-4c97-4b54-a5b8-2eeb1633d06d", "version": 1, "content_hash": "sha256:bc750a800a8b7f0bc3b86ba9404fda69d3d19a1a8deadd84a9ace1537940f6af" }, "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": "Dan Kondratyuk", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Lijun Yu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Xiuye Gu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "José Lezama", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Jonathan Huang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Rachel Hornung", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Hartwig Adam", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Hassan Akbari", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yair Alon", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Vighnesh Birodkar", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yong Cheng", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ming-Chang Chiu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Josh Dillon", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Irfan Essa", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Agrim Gupta", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Meera Hahn", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Anja Hauth", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "David Hendon", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Alonso Martinez", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "David Minnen", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "David Ross", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Grant Schindler", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Mikhail Sirotenko", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Kihyuk Sohn", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Krishna Somandepalli", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Huisheng Wang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Jimmy Yan", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ming-Hsuan Yang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Xuan Yang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Bryan Seybold", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Lu Jiang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } } ], "evidence": [ { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-0", "kind": "source_reference", "source": { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } } ], "origin": "HUMAN_LEGACY", "record_profile": "wrs-local-research-notes-0.1", "record_type": "research_note", "rrp_version": "0.1", "scope": { "description": "Autoregressive transformers and pretrained tokenizers are inherited. Acquired delta is unified multimodal training/task integration, not generic next-token modeling. Zero-shot generation in tested settings is not arbitrary-domain or long-horizon consistency.", "domain": "Multimodal sequence-generation systems" }, "sources": [ { "citation": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1" } ], "statement": "# Kondratyuk et al.: autoregressive multimodal video/audio generation\n\nTrained a decoder-only transformer on mixed multimodal generation objectives over video, image, text and audio representations, then adapted the pretrained model to conditioned video-generation tasks.\n\n## Scientific scope\n\nAutoregressive transformers and pretrained tokenizers are inherited. Acquired delta is unified multimodal training/task integration, not generic next-token modeling. Zero-shot generation in tested settings is not arbitrary-domain or long-horizon consistency.\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\nDan Kondratyuk; Lijun Yu; Xiuye Gu; José Lezama; Jonathan Huang; Rachel Hornung; Hartwig Adam; Hassan Akbari; Yair Alon; Vighnesh Birodkar; Yong Cheng; Ming-Chang Chiu; Josh Dillon; Irfan Essa; Agrim Gupta; Meera Hahn; Anja Hauth; David Hendon; Alonso Martinez; David Minnen; David Ross; Grant Schindler; Mikhail Sirotenko; Kihyuk Sohn; Krishna Somandepalli; Huisheng Wang; Jimmy Yan; Ming-Hsuan Yang; Xuan Yang; Bryan Seybold; Lu Jiang\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- [VideoPoet: A Large Language Model for Zero-Shot Video Generation](https://arxiv.org/abs/2312.14125v1)\n", "summary": "Trained a decoder-only transformer on mixed multimodal generation objectives over video, image, text and audio representations, then adapted the pretrained model to conditioned video-generation tasks.", "title": "Kondratyuk et al.: autoregressive multimodal video/audio generation" }, "record_id": "urn:uuid:5320e429-4c97-4b54-a5b8-2eeb1633d06d", "version": 1, "source_ref": { "record_id": "urn:uuid:5320e429-4c97-4b54-a5b8-2eeb1633d06d", "version": 1, "content_hash": "sha256:bc750a800a8b7f0bc3b86ba9404fda69d3d19a1a8deadd84a9ace1537940f6af" }, "export_view": "wrs-public-editorial-view-1", "public_view_hash": "sha256:8fd0e35cbcfec304f66b486382f839bd64e15dd00f258db67e947885d49e5a16" }, "target": { "record_id": "urn:uuid:5320e429-4c97-4b54-a5b8-2eeb1633d06d", "version": 1, "content_hash": "sha256:bc750a800a8b7f0bc3b86ba9404fda69d3d19a1a8deadd84a9ace1537940f6af" }, "published_grade": { "profile": "wrs-published-grade-1", "edition": "2026-10-28.1", "id": "kondratyuk-et-al-videopoet-token-generation-2023", "entry_id": "kondratyuk-et-al-videopoet-token-generation-2023", "revision": 1, "title": "Kondratyuk et al.: autoregressive multimodal video/audio generation", "context": "Multimodal sequence-generation systems", "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": "Trained a decoder-only transformer on mixed multimodal generation objectives over video, image, text and audio representations, then adapted the pretrained model to conditioned video-generation tasks.", "scope": "Trained a decoder-only transformer on mixed multimodal generation objectives over video, image, text and audio representations, then adapted the pretrained model to conditioned video-generation tasks. Autoregressive transformers and pretrained tokenizers are inherited. Acquired delta is unified multimodal training/task integration, not generic next-token modeling. Zero-shot generation in tested settings is not arbitrary-domain or long-horizon consistency.", "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. Autoregressive transformers and pretrained tokenizers are inherited. Acquired delta is unified multimodal training/task integration, not generic next-token modeling. Zero-shot generation in tested settings is not arbitrary-domain or long-horizon consistency.", "references": [ { "title": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "url": "https://arxiv.org/abs/2312.14125v1", "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:5320e429-4c97-4b54-a5b8-2eeb1633d06d", "version": 1, "content_hash": "sha256:bc750a800a8b7f0bc3b86ba9404fda69d3d19a1a8deadd84a9ace1537940f6af" }, "scientific_correctness_certified": false, "independent_expert_calibration": false, "method": "PROPRIETARY", "points": "80000" }, "canonical_agent_submission": false, "scientific_verification_awarded": false, "reader_guide": null, "reading_status": "SOURCE_LINKED_NOTE" }