{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H4QPS3XCKI3N63MWRF6TMEPQ7K","short_pith_number":"pith:H4QPS3XC","schema_version":"1.0","canonical_sha256":"3f20f96ee25236df6d96897d3611f0fa8f4ccff8cc8ff9047ff504c4205fed99","source":{"kind":"arxiv","id":"2502.03897","version":5},"attestation_state":"computed","paper":{"title":"UniForm: A Unified Multi-Task Diffusion Transformer for Audio-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Chi Zhang, Dongxu Ge, Fangqiu Yi, Lei Zhao, Linfeng Feng, Rujin Chen, Xiao-Lei Zhang, Xuelong Li","submitted_at":"2025-02-06T09:18:30Z","abstract_excerpt":"With the rise of diffusion models, audio-video generation has been revolutionized. However, most existing methods rely on separate modules for each modality, with limited exploration of unified generative architectures. In addition, many are confined to a single task and small-scale datasets. To overcome these limitations, we introduce UniForm, a unified multi-task diffusion transformer that generates both audio and visual modalities in a shared latent space. By using a unified denoising network, UniForm captures the inherent correlations between sound and vision. Additionally, we propose task"},"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":"2502.03897","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-02-06T09:18:30Z","cross_cats_sorted":["cs.AI","cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"a2a816e70cb2d5f216367fb2a67127aa2b7783514998ea695076290629934fd7","abstract_canon_sha256":"442009d2dcc0eca198095df2209e81553bbfef20c08997c2aad0af3f33263f36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:24.416512Z","signature_b64":"vxaIqVvk9Mf7lsvnyzUS7a/7F4IXSbNezGpA4K7c4p1ePh/f/+nV0yZYQYTAJkJ/zxPlZI5nRYZG3rLy0FDhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f20f96ee25236df6d96897d3611f0fa8f4ccff8cc8ff9047ff504c4205fed99","last_reissued_at":"2026-07-05T11:32:24.416020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:24.416020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniForm: A Unified Multi-Task Diffusion Transformer for Audio-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Chi Zhang, Dongxu Ge, Fangqiu Yi, Lei Zhao, Linfeng Feng, Rujin Chen, Xiao-Lei Zhang, Xuelong Li","submitted_at":"2025-02-06T09:18:30Z","abstract_excerpt":"With the rise of diffusion models, audio-video generation has been revolutionized. However, most existing methods rely on separate modules for each modality, with limited exploration of unified generative architectures. In addition, many are confined to a single task and small-scale datasets. To overcome these limitations, we introduce UniForm, a unified multi-task diffusion transformer that generates both audio and visual modalities in a shared latent space. By using a unified denoising network, UniForm captures the inherent correlations between sound and vision. Additionally, we propose task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03897","kind":"arxiv","version":5},"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/2502.03897/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":"2502.03897","created_at":"2026-07-05T11:32:24.416077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.03897v5","created_at":"2026-07-05T11:32:24.416077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03897","created_at":"2026-07-05T11:32:24.416077+00:00"},{"alias_kind":"pith_short_12","alias_value":"H4QPS3XCKI3N","created_at":"2026-07-05T11:32:24.416077+00:00"},{"alias_kind":"pith_short_16","alias_value":"H4QPS3XCKI3N63MW","created_at":"2026-07-05T11:32:24.416077+00:00"},{"alias_kind":"pith_short_8","alias_value":"H4QPS3XC","created_at":"2026-07-05T11:32:24.416077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03183","citing_title":"Inference-Time Scaling for Joint Audio-Video Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08729","citing_title":"Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20183","citing_title":"MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23994","citing_title":"PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20183","citing_title":"MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23994","citing_title":"PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12179","citing_title":"SyncDPO: Enhancing Temporal Synchronization in Video-Audio Joint Generation via Preference Learning","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08729","citing_title":"Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H4QPS3XCKI3N63MWRF6TMEPQ7K","json":"https://pith.science/pith/H4QPS3XCKI3N63MWRF6TMEPQ7K.json","graph_json":"https://pith.science/api/pith-number/H4QPS3XCKI3N63MWRF6TMEPQ7K/graph.json","events_json":"https://pith.science/api/pith-number/H4QPS3XCKI3N63MWRF6TMEPQ7K/events.json","paper":"https://pith.science/paper/H4QPS3XC"},"agent_actions":{"view_html":"https://pith.science/pith/H4QPS3XCKI3N63MWRF6TMEPQ7K","download_json":"https://pith.science/pith/H4QPS3XCKI3N63MWRF6TMEPQ7K.json","view_paper":"https://pith.science/paper/H4QPS3XC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.03897&json=true","fetch_graph":"https://pith.science/api/pith-number/H4QPS3XCKI3N63MWRF6TMEPQ7K/graph.json","fetch_events":"https://pith.science/api/pith-number/H4QPS3XCKI3N63MWRF6TMEPQ7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H4QPS3XCKI3N63MWRF6TMEPQ7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H4QPS3XCKI3N63MWRF6TMEPQ7K/action/storage_attestation","attest_author":"https://pith.science/pith/H4QPS3XCKI3N63MWRF6TMEPQ7K/action/author_attestation","sign_citation":"https://pith.science/pith/H4QPS3XCKI3N63MWRF6TMEPQ7K/action/citation_signature","submit_replication":"https://pith.science/pith/H4QPS3XCKI3N63MWRF6TMEPQ7K/action/replication_record"}},"created_at":"2026-07-05T11:32:24.416077+00:00","updated_at":"2026-07-05T11:32:24.416077+00:00"}