{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AIU6S2CDYAS2QYY73QLRLKO5JI","short_pith_number":"pith:AIU6S2CD","schema_version":"1.0","canonical_sha256":"0229e96843c025a8631fdc1715a9dd4a190bbe98730335fc0fd591d9dd8e1cf8","source":{"kind":"arxiv","id":"2508.08248","version":1},"attestation_state":"computed","paper":{"title":"StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong Luo, Qi Dai, Shuyuan Tu, Xintong Han, Yinming Huang, Yueming Pan, Yu-Gang Jiang, Zhen Xing, Zuxuan Wu","submitted_at":"2025-08-11T17:58:24Z","abstract_excerpt":"Current diffusion models for audio-driven avatar video generation struggle to synthesize long videos with natural audio synchronization and identity consistency. This paper presents StableAvatar, the first end-to-end video diffusion transformer that synthesizes infinite-length high-quality videos without post-processing. Conditioned on a reference image and audio, StableAvatar integrates tailored training and inference modules to enable infinite-length video generation. We observe that the main reason preventing existing models from generating long videos lies in their audio modeling. They typ"},"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":"2508.08248","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T17:58:24Z","cross_cats_sorted":[],"title_canon_sha256":"c90aaa6dd6f2308c028d9e9b39658dfaa721c99cd3b3aac907add43bcc5cf65e","abstract_canon_sha256":"e4a73ad71ddd6c419abe2664f98c4090c4abdf172dfd1f7add82c8d5c863a087"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:10.286916Z","signature_b64":"lyhJqE9SuRcAmNqEXEYPr6mFdgxVnTYl40CJ0lrTdVV1KCNli5TPK+ES2PIOCdKVvp4SzjrE22V8pP5VC9XeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0229e96843c025a8631fdc1715a9dd4a190bbe98730335fc0fd591d9dd8e1cf8","last_reissued_at":"2026-07-05T11:52:10.286439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:10.286439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong Luo, Qi Dai, Shuyuan Tu, Xintong Han, Yinming Huang, Yueming Pan, Yu-Gang Jiang, Zhen Xing, Zuxuan Wu","submitted_at":"2025-08-11T17:58:24Z","abstract_excerpt":"Current diffusion models for audio-driven avatar video generation struggle to synthesize long videos with natural audio synchronization and identity consistency. This paper presents StableAvatar, the first end-to-end video diffusion transformer that synthesizes infinite-length high-quality videos without post-processing. Conditioned on a reference image and audio, StableAvatar integrates tailored training and inference modules to enable infinite-length video generation. We observe that the main reason preventing existing models from generating long videos lies in their audio modeling. They typ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08248","kind":"arxiv","version":1},"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/2508.08248/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":"2508.08248","created_at":"2026-07-05T11:52:10.286498+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.08248v1","created_at":"2026-07-05T11:52:10.286498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08248","created_at":"2026-07-05T11:52:10.286498+00:00"},{"alias_kind":"pith_short_12","alias_value":"AIU6S2CDYAS2","created_at":"2026-07-05T11:52:10.286498+00:00"},{"alias_kind":"pith_short_16","alias_value":"AIU6S2CDYAS2QYY7","created_at":"2026-07-05T11:52:10.286498+00:00"},{"alias_kind":"pith_short_8","alias_value":"AIU6S2CD","created_at":"2026-07-05T11:52:10.286498+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22905","citing_title":"InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01222","citing_title":"Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models","ref_index":48,"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":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17248","citing_title":"Image-to-Video Diffusion: From Foundations to Open Frontiers","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2512.04677","citing_title":"Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13669","citing_title":"EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27918","citing_title":"Generate Your Talking Avatar from Video Reference","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02948","citing_title":"AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10367","citing_title":"Beyond Monologue: Interactive Talking-Listening Avatar Generation with Conversational Audio Context-Aware Kernels","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07823","citing_title":"LPM 1.0: Video-based Character Performance Model","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02948","citing_title":"AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AIU6S2CDYAS2QYY73QLRLKO5JI","json":"https://pith.science/pith/AIU6S2CDYAS2QYY73QLRLKO5JI.json","graph_json":"https://pith.science/api/pith-number/AIU6S2CDYAS2QYY73QLRLKO5JI/graph.json","events_json":"https://pith.science/api/pith-number/AIU6S2CDYAS2QYY73QLRLKO5JI/events.json","paper":"https://pith.science/paper/AIU6S2CD"},"agent_actions":{"view_html":"https://pith.science/pith/AIU6S2CDYAS2QYY73QLRLKO5JI","download_json":"https://pith.science/pith/AIU6S2CDYAS2QYY73QLRLKO5JI.json","view_paper":"https://pith.science/paper/AIU6S2CD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.08248&json=true","fetch_graph":"https://pith.science/api/pith-number/AIU6S2CDYAS2QYY73QLRLKO5JI/graph.json","fetch_events":"https://pith.science/api/pith-number/AIU6S2CDYAS2QYY73QLRLKO5JI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AIU6S2CDYAS2QYY73QLRLKO5JI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AIU6S2CDYAS2QYY73QLRLKO5JI/action/storage_attestation","attest_author":"https://pith.science/pith/AIU6S2CDYAS2QYY73QLRLKO5JI/action/author_attestation","sign_citation":"https://pith.science/pith/AIU6S2CDYAS2QYY73QLRLKO5JI/action/citation_signature","submit_replication":"https://pith.science/pith/AIU6S2CDYAS2QYY73QLRLKO5JI/action/replication_record"}},"created_at":"2026-07-05T11:52:10.286498+00:00","updated_at":"2026-07-05T11:52:10.286498+00:00"}