{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3LVSUYGFQX6DCEXMJ3SC7W2UYV","short_pith_number":"pith:3LVSUYGF","schema_version":"1.0","canonical_sha256":"daeb2a60c585fc3112ec4ee42fdb54c57a47a016732e7e61ffabe8951f5c6d14","source":{"kind":"arxiv","id":"2505.20156","version":2},"attestation_state":"computed","paper":{"title":"HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junshu Tang, Qinglin Lu, Qin Lin, Sen Liang, Yi Chen, Yifeng Ma, Yuan Zhou, Zixiang Zhou, Ziyao Huang","submitted_at":"2025-05-26T15:57:27Z","abstract_excerpt":"Recent years have witnessed significant progress in audio-driven human animation. However, critical challenges remain in (i) generating highly dynamic videos while preserving character consistency, (ii) achieving precise emotion alignment between characters and audio, and (iii) enabling multi-character audio-driven animation. To address these challenges, we propose HunyuanVideo-Avatar, a multimodal diffusion transformer (MM-DiT)-based model capable of simultaneously generating dynamic, emotion-controllable, and multi-character dialogue videos. Concretely, HunyuanVideo-Avatar introduces three k"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.20156","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T15:57:27Z","cross_cats_sorted":[],"title_canon_sha256":"a2a9190d9e3559c33f6dcbc9bcb250da5d5103e2260bfa6245322e8d1b82467f","abstract_canon_sha256":"4846fb239ca15d8db98f20b12dab82302205cced3d73e891dcf03b645fa6a3ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:00.323987Z","signature_b64":"vNd8BAq0pzZZvGjnh6JvvYXhfvBFy5NjWo3v5oaaZubnN/8R12ewHCWo+r6HmjOdZrfa0yhTrgso2HHFXzEPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"daeb2a60c585fc3112ec4ee42fdb54c57a47a016732e7e61ffabe8951f5c6d14","last_reissued_at":"2026-07-05T11:15:00.323512Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:00.323512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junshu Tang, Qinglin Lu, Qin Lin, Sen Liang, Yi Chen, Yifeng Ma, Yuan Zhou, Zixiang Zhou, Ziyao Huang","submitted_at":"2025-05-26T15:57:27Z","abstract_excerpt":"Recent years have witnessed significant progress in audio-driven human animation. However, critical challenges remain in (i) generating highly dynamic videos while preserving character consistency, (ii) achieving precise emotion alignment between characters and audio, and (iii) enabling multi-character audio-driven animation. To address these challenges, we propose HunyuanVideo-Avatar, a multimodal diffusion transformer (MM-DiT)-based model capable of simultaneously generating dynamic, emotion-controllable, and multi-character dialogue videos. Concretely, HunyuanVideo-Avatar introduces three k"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20156","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.20156/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2505.20156","created_at":"2026-07-05T11:15:00.323570+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20156v2","created_at":"2026-07-05T11:15:00.323570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20156","created_at":"2026-07-05T11:15:00.323570+00:00"},{"alias_kind":"pith_short_12","alias_value":"3LVSUYGFQX6D","created_at":"2026-07-05T11:15:00.323570+00:00"},{"alias_kind":"pith_short_16","alias_value":"3LVSUYGFQX6DCEXM","created_at":"2026-07-05T11:15:00.323570+00:00"},{"alias_kind":"pith_short_8","alias_value":"3LVSUYGF","created_at":"2026-07-05T11:15:00.323570+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18326","citing_title":"OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22905","citing_title":"InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30849","citing_title":"SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22905","citing_title":"InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15042","citing_title":"EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26486","citing_title":"LongCat-Video-Avatar 1.5 Technical Report","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30083","citing_title":"Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17248","citing_title":"Image-to-Video Diffusion: From Foundations to Open Frontiers","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13669","citing_title":"EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27918","citing_title":"Generate Your Talking Avatar from Video Reference","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10079","citing_title":"SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23629","citing_title":"From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation","ref_index":239,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23629","citing_title":"From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation","ref_index":239,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11804","citing_title":"OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09057","citing_title":"Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherence","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06912","citing_title":"Advancing Reliable Synthetic Video Detection: Insights from the SAFE Challenge","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18326","citing_title":"OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3LVSUYGFQX6DCEXMJ3SC7W2UYV","json":"https://pith.science/pith/3LVSUYGFQX6DCEXMJ3SC7W2UYV.json","graph_json":"https://pith.science/api/pith-number/3LVSUYGFQX6DCEXMJ3SC7W2UYV/graph.json","events_json":"https://pith.science/api/pith-number/3LVSUYGFQX6DCEXMJ3SC7W2UYV/events.json","paper":"https://pith.science/paper/3LVSUYGF"},"agent_actions":{"view_html":"https://pith.science/pith/3LVSUYGFQX6DCEXMJ3SC7W2UYV","download_json":"https://pith.science/pith/3LVSUYGFQX6DCEXMJ3SC7W2UYV.json","view_paper":"https://pith.science/paper/3LVSUYGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20156&json=true","fetch_graph":"https://pith.science/api/pith-number/3LVSUYGFQX6DCEXMJ3SC7W2UYV/graph.json","fetch_events":"https://pith.science/api/pith-number/3LVSUYGFQX6DCEXMJ3SC7W2UYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3LVSUYGFQX6DCEXMJ3SC7W2UYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3LVSUYGFQX6DCEXMJ3SC7W2UYV/action/storage_attestation","attest_author":"https://pith.science/pith/3LVSUYGFQX6DCEXMJ3SC7W2UYV/action/author_attestation","sign_citation":"https://pith.science/pith/3LVSUYGFQX6DCEXMJ3SC7W2UYV/action/citation_signature","submit_replication":"https://pith.science/pith/3LVSUYGFQX6DCEXMJ3SC7W2UYV/action/replication_record"}},"created_at":"2026-07-05T11:15:00.323570+00:00","updated_at":"2026-07-05T11:15:00.323570+00:00"}