{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:46AFKBCPA3OAWJBXVUE2DAQYU5","short_pith_number":"pith:46AFKBCP","schema_version":"1.0","canonical_sha256":"e78055044f06dc0b2437ad09a18218a75772f2270f3ff96839087bb104ba4b7d","source":{"kind":"arxiv","id":"2412.15191","version":2},"attestation_state":"computed","paper":{"title":"AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Alper Canberk, Ivan Skorokhodov, Kwot Sin Lee, Moayed Haji-Ali, Sergey Tulyakov, Vicente Ordonez, Willi Menapace","submitted_at":"2024-12-19T18:57:21Z","abstract_excerpt":"We propose AV-Link, a unified framework for Video-to-Audio (A2V) and Audio-to-Video (A2V) generation that leverages the activations of frozen video and audio diffusion models for temporally-aligned cross-modal conditioning. The key to our framework is a Fusion Block that facilitates bidirectional information exchange between video and audio diffusion models through temporally-aligned self attention operations. Unlike prior work that uses dedicated models for A2V and V2A tasks and relies on pretrained feature extractors, AV-Link achieves both tasks in a single self-contained framework, directly"},"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":"2412.15191","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T18:57:21Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"45339ab807f2d9a2f8b70f895ad550ee3e59ae520be2486b9b3753f71991ca79","abstract_canon_sha256":"29dd374d00d3ba23b8fd3df1f58a3f39528e4c4a6b6d03998fd8eb95761d18ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:31.288688Z","signature_b64":"QHBXG1RvblfNPfETzgcehrZ5OY6B3JVn7MMHPhLkCXQNBZ2gVs6JfsSH9YjTZZUHsVlolP3h2UalKlQ2QwZeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e78055044f06dc0b2437ad09a18218a75772f2270f3ff96839087bb104ba4b7d","last_reissued_at":"2026-07-05T10:28:31.287801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:31.287801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Alper Canberk, Ivan Skorokhodov, Kwot Sin Lee, Moayed Haji-Ali, Sergey Tulyakov, Vicente Ordonez, Willi Menapace","submitted_at":"2024-12-19T18:57:21Z","abstract_excerpt":"We propose AV-Link, a unified framework for Video-to-Audio (A2V) and Audio-to-Video (A2V) generation that leverages the activations of frozen video and audio diffusion models for temporally-aligned cross-modal conditioning. The key to our framework is a Fusion Block that facilitates bidirectional information exchange between video and audio diffusion models through temporally-aligned self attention operations. Unlike prior work that uses dedicated models for A2V and V2A tasks and relies on pretrained feature extractors, AV-Link achieves both tasks in a single self-contained framework, directly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15191","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/2412.15191/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":"2412.15191","created_at":"2026-07-05T10:28:31.287914+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15191v2","created_at":"2026-07-05T10:28:31.287914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15191","created_at":"2026-07-05T10:28:31.287914+00:00"},{"alias_kind":"pith_short_12","alias_value":"46AFKBCPA3OA","created_at":"2026-07-05T10:28:31.287914+00:00"},{"alias_kind":"pith_short_16","alias_value":"46AFKBCPA3OAWJBX","created_at":"2026-07-05T10:28:31.287914+00:00"},{"alias_kind":"pith_short_8","alias_value":"46AFKBCP","created_at":"2026-07-05T10:28:31.287914+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/46AFKBCPA3OAWJBXVUE2DAQYU5","json":"https://pith.science/pith/46AFKBCPA3OAWJBXVUE2DAQYU5.json","graph_json":"https://pith.science/api/pith-number/46AFKBCPA3OAWJBXVUE2DAQYU5/graph.json","events_json":"https://pith.science/api/pith-number/46AFKBCPA3OAWJBXVUE2DAQYU5/events.json","paper":"https://pith.science/paper/46AFKBCP"},"agent_actions":{"view_html":"https://pith.science/pith/46AFKBCPA3OAWJBXVUE2DAQYU5","download_json":"https://pith.science/pith/46AFKBCPA3OAWJBXVUE2DAQYU5.json","view_paper":"https://pith.science/paper/46AFKBCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15191&json=true","fetch_graph":"https://pith.science/api/pith-number/46AFKBCPA3OAWJBXVUE2DAQYU5/graph.json","fetch_events":"https://pith.science/api/pith-number/46AFKBCPA3OAWJBXVUE2DAQYU5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46AFKBCPA3OAWJBXVUE2DAQYU5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46AFKBCPA3OAWJBXVUE2DAQYU5/action/storage_attestation","attest_author":"https://pith.science/pith/46AFKBCPA3OAWJBXVUE2DAQYU5/action/author_attestation","sign_citation":"https://pith.science/pith/46AFKBCPA3OAWJBXVUE2DAQYU5/action/citation_signature","submit_replication":"https://pith.science/pith/46AFKBCPA3OAWJBXVUE2DAQYU5/action/replication_record"}},"created_at":"2026-07-05T10:28:31.287914+00:00","updated_at":"2026-07-05T10:28:31.287914+00:00"}