{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5C57ZJUT56YNU2HVVFP7NVM2F7","short_pith_number":"pith:5C57ZJUT","schema_version":"1.0","canonical_sha256":"e8bbfca693efb0da68f5a95ff6d59a2fd1369fbf5e0c087db084ffdb3b627d5c","source":{"kind":"arxiv","id":"2405.13762","version":1},"attestation_state":"computed","paper":{"title":"A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Agrim Gupta, Alonso Martinez, Aren Jansen, Brendan Jou, Gwanghyun Kim, Jacob Walker, Jos\\'e Lezama, Krishna Somandepalli, Lijun Yu, Lu Jiang, Yu-Chuan Su","submitted_at":"2024-05-22T15:47:14Z","abstract_excerpt":"Training diffusion models for audiovisual sequences allows for a range of generation tasks by learning conditional distributions of various input-output combinations of the two modalities. Nevertheless, this strategy often requires training a separate model for each task which is expensive. Here, we propose a novel training approach to effectively learn arbitrary conditional distributions in the audiovisual space.Our key contribution lies in how we parameterize the diffusion timestep in the forward diffusion process. Instead of the standard fixed diffusion timestep, we propose applying variabl"},"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":"2405.13762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-22T15:47:14Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"18fa683a752e43bfb983080ecee1f073336f2ad6772c40ce56919c12eba5ff1b","abstract_canon_sha256":"2dab8c32093b1d6753b0a55fb5750cd74b89b4a3f0ba745a87cba14a91db2984"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:12.365209Z","signature_b64":"A/YT+AMFGA+7e9DoUPCrPc6gAuNbukD4yB5A6QL76sW7NBc84pDVa49L8KLf5HjXiSUAkD8DYXqMn2YJP5ifBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8bbfca693efb0da68f5a95ff6d59a2fd1369fbf5e0c087db084ffdb3b627d5c","last_reissued_at":"2026-07-05T11:18:12.364744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:12.364744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Agrim Gupta, Alonso Martinez, Aren Jansen, Brendan Jou, Gwanghyun Kim, Jacob Walker, Jos\\'e Lezama, Krishna Somandepalli, Lijun Yu, Lu Jiang, Yu-Chuan Su","submitted_at":"2024-05-22T15:47:14Z","abstract_excerpt":"Training diffusion models for audiovisual sequences allows for a range of generation tasks by learning conditional distributions of various input-output combinations of the two modalities. Nevertheless, this strategy often requires training a separate model for each task which is expensive. Here, we propose a novel training approach to effectively learn arbitrary conditional distributions in the audiovisual space.Our key contribution lies in how we parameterize the diffusion timestep in the forward diffusion process. Instead of the standard fixed diffusion timestep, we propose applying variabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13762","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/2405.13762/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":"2405.13762","created_at":"2026-07-05T11:18:12.364800+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.13762v1","created_at":"2026-07-05T11:18:12.364800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13762","created_at":"2026-07-05T11:18:12.364800+00:00"},{"alias_kind":"pith_short_12","alias_value":"5C57ZJUT56YN","created_at":"2026-07-05T11:18:12.364800+00:00"},{"alias_kind":"pith_short_16","alias_value":"5C57ZJUT56YNU2HV","created_at":"2026-07-05T11:18:12.364800+00:00"},{"alias_kind":"pith_short_8","alias_value":"5C57ZJUT","created_at":"2026-07-05T11:18:12.364800+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5C57ZJUT56YNU2HVVFP7NVM2F7","json":"https://pith.science/pith/5C57ZJUT56YNU2HVVFP7NVM2F7.json","graph_json":"https://pith.science/api/pith-number/5C57ZJUT56YNU2HVVFP7NVM2F7/graph.json","events_json":"https://pith.science/api/pith-number/5C57ZJUT56YNU2HVVFP7NVM2F7/events.json","paper":"https://pith.science/paper/5C57ZJUT"},"agent_actions":{"view_html":"https://pith.science/pith/5C57ZJUT56YNU2HVVFP7NVM2F7","download_json":"https://pith.science/pith/5C57ZJUT56YNU2HVVFP7NVM2F7.json","view_paper":"https://pith.science/paper/5C57ZJUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.13762&json=true","fetch_graph":"https://pith.science/api/pith-number/5C57ZJUT56YNU2HVVFP7NVM2F7/graph.json","fetch_events":"https://pith.science/api/pith-number/5C57ZJUT56YNU2HVVFP7NVM2F7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5C57ZJUT56YNU2HVVFP7NVM2F7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5C57ZJUT56YNU2HVVFP7NVM2F7/action/storage_attestation","attest_author":"https://pith.science/pith/5C57ZJUT56YNU2HVVFP7NVM2F7/action/author_attestation","sign_citation":"https://pith.science/pith/5C57ZJUT56YNU2HVVFP7NVM2F7/action/citation_signature","submit_replication":"https://pith.science/pith/5C57ZJUT56YNU2HVVFP7NVM2F7/action/replication_record"}},"created_at":"2026-07-05T11:18:12.364800+00:00","updated_at":"2026-07-05T11:18:12.364800+00:00"}