{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CRZPAPKXJPOXLUEXGPFLJY3DFI","short_pith_number":"pith:CRZPAPKX","schema_version":"1.0","canonical_sha256":"1472f03d574bdd75d09733cab4e3632a17170d01c6e39b857b36a5aa06a2afc4","source":{"kind":"arxiv","id":"2510.01284","version":1},"attestation_state":"computed","paper":{"title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Ovi generates audio and video together in one process by fusing twin identical diffusion transformers block by block.","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Calder Katyal, Chetwin Low, Weimin Wang","submitted_at":"2025-09-30T21:03:50Z","abstract_excerpt":"Audio-video generation has often relied on complex multi-stage architectures or sequential synthesis of sound and visuals. We introduce Ovi, a unified paradigm for audio-video generation that models the two modalities as a single generative process. By using blockwise cross-modal fusion of twin-DiT modules, Ovi achieves natural synchronization and removes the need for separate pipelines or post hoc alignment. To facilitate fine-grained multimodal fusion modeling, we initialize an audio tower with an architecture identical to that of a strong pretrained video model. Trained from scratch on hund"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2510.01284","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-09-30T21:03:50Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"eaf2258893cf6399b57c826c3db6ad000d9d95ddfa1b691dfd5fb7a996ec484a","abstract_canon_sha256":"7ce7d15b63daa02ae8b8851c614d09cbf19336f1adae2c17ef4b109714a5f876"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:46.035782Z","signature_b64":"0/e/j6Y++t3lvnDioOpVMg84/K0qtCo7JyGgy9BZ9N/ETRgCSoSdgJ0HuU+rXrM4NmB0TeNpTM8deMP1KGJpCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1472f03d574bdd75d09733cab4e3632a17170d01c6e39b857b36a5aa06a2afc4","last_reissued_at":"2026-05-17T23:38:46.035192Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:46.035192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Ovi generates audio and video together in one process by fusing twin identical diffusion transformers block by block.","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Calder Katyal, Chetwin Low, Weimin Wang","submitted_at":"2025-09-30T21:03:50Z","abstract_excerpt":"Audio-video generation has often relied on complex multi-stage architectures or sequential synthesis of sound and visuals. We introduce Ovi, a unified paradigm for audio-video generation that models the two modalities as a single generative process. By using blockwise cross-modal fusion of twin-DiT modules, Ovi achieves natural synchronization and removes the need for separate pipelines or post hoc alignment. To facilitate fine-grained multimodal fusion modeling, we initialize an audio tower with an architecture identical to that of a strong pretrained video model. Trained from scratch on hund"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By using blockwise cross-modal fusion of twin-DiT modules, Ovi achieves natural synchronization and removes the need for separate pipelines or post hoc alignment.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That initializing an audio tower with an architecture identical to a strong pretrained video model and then jointly training via bidirectional cross-attention on a vast video corpus will produce reliable cross-modal timing and semantic alignment without additional alignment losses or post-processing.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A single generative model uses twin DiT backbones with blockwise cross-attention and scaled-RoPE timing exchange to synthesize synchronized audio-video directly.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Ovi generates audio and video together in one process by fusing twin identical diffusion transformers block by block.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0a6ffc5657c0aa9898b238dbae0f54c6ad4605fe468ffdffa0f699d84adce477"},"source":{"id":"2510.01284","kind":"arxiv","version":1},"verdict":{"id":"cd90296c-aac0-4d45-af8b-ff608b2ecbbf","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T00:58:33.434002Z","strongest_claim":"By using blockwise cross-modal fusion of twin-DiT modules, Ovi achieves natural synchronization and removes the need for separate pipelines or post hoc alignment.","one_line_summary":"A single generative model uses twin DiT backbones with blockwise cross-attention and scaled-RoPE timing exchange to synthesize synchronized audio-video directly.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That initializing an audio tower with an architecture identical to a strong pretrained video model and then jointly training via bidirectional cross-attention on a vast video corpus will produce reliable cross-modal timing and semantic alignment without additional alignment losses or post-processing.","pith_extraction_headline":"Ovi generates audio and video together in one process by fusing twin identical diffusion transformers block by block."},"references":{"count":20,"sample":[{"doi":"","year":null,"title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","work_id":"6e88ee95-1133-4302-a142-cdf8f9456a8d","ref_index":1,"cited_arxiv_id":"2406.02430","is_internal_anchor":true},{"doi":"","year":2025,"title":"com/research/video-generation-models-as-world-simulators","work_id":"e01a4ca3-169f-41c9-adf9-19a9dd64a994","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"HuMo: Human-centric video generation via collaborative multi-modal conditioning","work_id":"313111a9-b492-44f5-bf1f-6b5c2c642abf","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","work_id":"e5ad925a-4045-49b5-b301-208bcbf3eca8","ref_index":4,"cited_arxiv_id":"2407.05407","is_internal_anchor":true},{"doi":"","year":null,"title":"Ace-step: A step towards music generation foundation model.arXiv preprint arXiv:2506.00045","work_id":"0d4831b4-71c3-4405-b540-1683d26109f6","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":20,"snapshot_sha256":"82668244fa647f84970ed0b7ad60dd132801c0e8ed2357f8d3cfae7048cb0fe5","internal_anchors":6},"formal_canon":{"evidence_count":2,"snapshot_sha256":"dcc63dfbc2e0470515064e223638b706ac28e96ca692fa011a4f85b128f3a7aa"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2510.01284","created_at":"2026-05-17T23:38:46.035277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.01284v1","created_at":"2026-05-17T23:38:46.035277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.01284","created_at":"2026-05-17T23:38:46.035277+00:00"},{"alias_kind":"pith_short_12","alias_value":"CRZPAPKXJPOX","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"CRZPAPKXJPOXLUEX","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"CRZPAPKX","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":20,"sample":[{"citing_arxiv_id":"2512.23994","citing_title":"PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17488","citing_title":"Omni-Customizer: End-to-End MultiModal Customization for Joint Audio-Video Generation","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18467","citing_title":"InstructAV2AV: Instruction-Guided Audio-Video Joint Editing","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2512.10571","citing_title":"AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2512.23994","citing_title":"PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2601.22143","citing_title":"JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2603.12639","citing_title":"RoboStereo: Dual-Tower 4D Embodied World Models for Unified Policy Optimization","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2601.03233","citing_title":"LTX-2: Efficient Joint Audio-Visual Foundation Model","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12179","citing_title":"SyncDPO: Enhancing Temporal Synchronization in Video-Audio Joint Generation via Preference Learning","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11723","citing_title":"CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08729","citing_title":"Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25819","citing_title":"Mutual Forcing: Dual-Mode Self-Evolution for Fast Autoregressive Audio-Video Character Generation","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23586","citing_title":"Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23632","citing_title":"Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01809","citing_title":"TMD-Bench: A Multi-Level Evaluation Paradigm for Music-Dance Co-Generation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11804","citing_title":"OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10367","citing_title":"Beyond Monologue: Interactive Talking-Listening Avatar Generation with Conversational Audio Context-Aware Kernels","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09057","citing_title":"Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherence","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07061","citing_title":"Do Joint Audio-Video Generation Models Understand Physics?","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18326","citing_title":"OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CRZPAPKXJPOXLUEXGPFLJY3DFI","json":"https://pith.science/pith/CRZPAPKXJPOXLUEXGPFLJY3DFI.json","graph_json":"https://pith.science/api/pith-number/CRZPAPKXJPOXLUEXGPFLJY3DFI/graph.json","events_json":"https://pith.science/api/pith-number/CRZPAPKXJPOXLUEXGPFLJY3DFI/events.json","paper":"https://pith.science/paper/CRZPAPKX"},"agent_actions":{"view_html":"https://pith.science/pith/CRZPAPKXJPOXLUEXGPFLJY3DFI","download_json":"https://pith.science/pith/CRZPAPKXJPOXLUEXGPFLJY3DFI.json","view_paper":"https://pith.science/paper/CRZPAPKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.01284&json=true","fetch_graph":"https://pith.science/api/pith-number/CRZPAPKXJPOXLUEXGPFLJY3DFI/graph.json","fetch_events":"https://pith.science/api/pith-number/CRZPAPKXJPOXLUEXGPFLJY3DFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CRZPAPKXJPOXLUEXGPFLJY3DFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CRZPAPKXJPOXLUEXGPFLJY3DFI/action/storage_attestation","attest_author":"https://pith.science/pith/CRZPAPKXJPOXLUEXGPFLJY3DFI/action/author_attestation","sign_citation":"https://pith.science/pith/CRZPAPKXJPOXLUEXGPFLJY3DFI/action/citation_signature","submit_replication":"https://pith.science/pith/CRZPAPKXJPOXLUEXGPFLJY3DFI/action/replication_record"}},"created_at":"2026-05-17T23:38:46.035277+00:00","updated_at":"2026-05-17T23:38:46.035277+00:00"}