{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5UWBZ4KNBDAIBIFSXOQSEVO6BV","short_pith_number":"pith:5UWBZ4KN","schema_version":"1.0","canonical_sha256":"ed2c1cf14d08c080a0b2bba12255de0d7d2ce248fb907f78b5f6e1cc693ad856","source":{"kind":"arxiv","id":"2506.23858","version":1},"attestation_state":"computed","paper":{"title":"VMoBA: Mixture-of-Block Attention for Video Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Zhang, Haotian Yang, Jianzong Wu, Liang Hou, Pengfei Wan, Xin Tao, Ye Tian, Yunhai Tong","submitted_at":"2025-06-30T13:52:31Z","abstract_excerpt":"The quadratic complexity of full attention mechanisms poses a significant bottleneck for Video Diffusion Models (VDMs) aiming to generate long-duration, high-resolution videos. While various sparse attention methods have been proposed, many are designed as training-free inference accelerators or do not optimally capture the unique spatio-temporal characteristics inherent in video data when trained natively. This paper introduces Video Mixture of Block Attention (VMoBA), a novel sparse attention mechanism specifically adapted for VDMs. Motivated by an in-depth analysis of attention patterns wit"},"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":"2506.23858","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T13:52:31Z","cross_cats_sorted":[],"title_canon_sha256":"fe903644f8981cfc9cdcaf746e1fa482c7a1a599c722c300610ac03af6ecb105","abstract_canon_sha256":"2008e9df02dc81171090c2179c75e3bd965f3b49eaf484e9eb83ad20effaf44b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:29.114197Z","signature_b64":"5SaSUYY/YsHySVuFNPNFL5GB8zMgrl2nWtgX6KyHuq8OX7ZhkJtFAzSTi1tKJ2BBxcPoDJjQDi/QPyNLf/LMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed2c1cf14d08c080a0b2bba12255de0d7d2ce248fb907f78b5f6e1cc693ad856","last_reissued_at":"2026-07-05T11:29:29.113682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:29.113682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VMoBA: Mixture-of-Block Attention for Video Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Zhang, Haotian Yang, Jianzong Wu, Liang Hou, Pengfei Wan, Xin Tao, Ye Tian, Yunhai Tong","submitted_at":"2025-06-30T13:52:31Z","abstract_excerpt":"The quadratic complexity of full attention mechanisms poses a significant bottleneck for Video Diffusion Models (VDMs) aiming to generate long-duration, high-resolution videos. While various sparse attention methods have been proposed, many are designed as training-free inference accelerators or do not optimally capture the unique spatio-temporal characteristics inherent in video data when trained natively. This paper introduces Video Mixture of Block Attention (VMoBA), a novel sparse attention mechanism specifically adapted for VDMs. Motivated by an in-depth analysis of attention patterns wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23858","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/2506.23858/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":"2506.23858","created_at":"2026-07-05T11:29:29.113751+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23858v1","created_at":"2026-07-05T11:29:29.113751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23858","created_at":"2026-07-05T11:29:29.113751+00:00"},{"alias_kind":"pith_short_12","alias_value":"5UWBZ4KNBDAI","created_at":"2026-07-05T11:29:29.113751+00:00"},{"alias_kind":"pith_short_16","alias_value":"5UWBZ4KNBDAIBIFS","created_at":"2026-07-05T11:29:29.113751+00:00"},{"alias_kind":"pith_short_8","alias_value":"5UWBZ4KN","created_at":"2026-07-05T11:29:29.113751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31158","citing_title":"Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30325","citing_title":"Veda: Scalable Video Diffusion via Distilled Sparse Attention","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2603.18636","citing_title":"Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14513","citing_title":"HASTE: Training-Free Video Diffusion Acceleration via Head-Wise Adaptive Sparse Attention","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12219","citing_title":"Ride the Wave: Precision-Allocated Sparse Attention for Smooth Video Generation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15911","citing_title":"Efficient Video Diffusion Models: Advancements and Challenges","ref_index":148,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5UWBZ4KNBDAIBIFSXOQSEVO6BV","json":"https://pith.science/pith/5UWBZ4KNBDAIBIFSXOQSEVO6BV.json","graph_json":"https://pith.science/api/pith-number/5UWBZ4KNBDAIBIFSXOQSEVO6BV/graph.json","events_json":"https://pith.science/api/pith-number/5UWBZ4KNBDAIBIFSXOQSEVO6BV/events.json","paper":"https://pith.science/paper/5UWBZ4KN"},"agent_actions":{"view_html":"https://pith.science/pith/5UWBZ4KNBDAIBIFSXOQSEVO6BV","download_json":"https://pith.science/pith/5UWBZ4KNBDAIBIFSXOQSEVO6BV.json","view_paper":"https://pith.science/paper/5UWBZ4KN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23858&json=true","fetch_graph":"https://pith.science/api/pith-number/5UWBZ4KNBDAIBIFSXOQSEVO6BV/graph.json","fetch_events":"https://pith.science/api/pith-number/5UWBZ4KNBDAIBIFSXOQSEVO6BV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5UWBZ4KNBDAIBIFSXOQSEVO6BV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5UWBZ4KNBDAIBIFSXOQSEVO6BV/action/storage_attestation","attest_author":"https://pith.science/pith/5UWBZ4KNBDAIBIFSXOQSEVO6BV/action/author_attestation","sign_citation":"https://pith.science/pith/5UWBZ4KNBDAIBIFSXOQSEVO6BV/action/citation_signature","submit_replication":"https://pith.science/pith/5UWBZ4KNBDAIBIFSXOQSEVO6BV/action/replication_record"}},"created_at":"2026-07-05T11:29:29.113751+00:00","updated_at":"2026-07-05T11:29:29.113751+00:00"}