{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SDGNTVAN7HQ2RQB634BV25OGUY","short_pith_number":"pith:SDGNTVAN","schema_version":"1.0","canonical_sha256":"90ccd9d40df9e1a8c03edf035d75c6a60937059bc4ab3722cde89da0c89d25bb","source":{"kind":"arxiv","id":"2410.20280","version":1},"attestation_state":"computed","paper":{"title":"MarDini: Masked Autoregressive Diffusion for Video Generation at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ding Liu, Haozhe Liu, Juan C. P\\'erez, Juan-Manuel P\\'erez-R\\'ua, Jui-Chieh Wu, J\\\"urgen Schmidhuber, Kumara Kahatapitiya, Menglin Jia, Mengmeng Xu, Sen He, Shikun Liu, Tao Xiang, Xiao Han, Yanping Xie, Zijian Zhou","submitted_at":"2024-10-26T21:12:32Z","abstract_excerpt":"We introduce MarDini, a new family of video diffusion models that integrate the advantages of masked auto-regression (MAR) into a unified diffusion model (DM) framework. Here, MAR handles temporal planning, while DM focuses on spatial generation in an asymmetric network design: i) a MAR-based planning model containing most of the parameters generates planning signals for each masked frame using low-resolution input; ii) a lightweight generation model uses these signals to produce high-resolution frames via diffusion de-noising. MarDini's MAR enables video generation conditioned on any number o"},"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":"2410.20280","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-26T21:12:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3caeefd940d41652d9dba2ed9eee257ee92ab3b6b0f8ea6500945c4be5665a94","abstract_canon_sha256":"86c448e6e0745d1041019be9f18793bcf350cada7fdf773a8290aacba9f84273"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:42.019329Z","signature_b64":"LE/9W1kszVwtmjaQERmdy7vlXKbxlnxOCljsnYK/ZfihWyQxPuvWwIPajgEzYd4elg50JC57f6h9+ajSytjgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90ccd9d40df9e1a8c03edf035d75c6a60937059bc4ab3722cde89da0c89d25bb","last_reissued_at":"2026-07-05T09:26:42.018827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:42.018827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MarDini: Masked Autoregressive Diffusion for Video Generation at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ding Liu, Haozhe Liu, Juan C. P\\'erez, Juan-Manuel P\\'erez-R\\'ua, Jui-Chieh Wu, J\\\"urgen Schmidhuber, Kumara Kahatapitiya, Menglin Jia, Mengmeng Xu, Sen He, Shikun Liu, Tao Xiang, Xiao Han, Yanping Xie, Zijian Zhou","submitted_at":"2024-10-26T21:12:32Z","abstract_excerpt":"We introduce MarDini, a new family of video diffusion models that integrate the advantages of masked auto-regression (MAR) into a unified diffusion model (DM) framework. Here, MAR handles temporal planning, while DM focuses on spatial generation in an asymmetric network design: i) a MAR-based planning model containing most of the parameters generates planning signals for each masked frame using low-resolution input; ii) a lightweight generation model uses these signals to produce high-resolution frames via diffusion de-noising. MarDini's MAR enables video generation conditioned on any number o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20280","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/2410.20280/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":"2410.20280","created_at":"2026-07-05T09:26:42.018885+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20280v1","created_at":"2026-07-05T09:26:42.018885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20280","created_at":"2026-07-05T09:26:42.018885+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDGNTVAN7HQ2","created_at":"2026-07-05T09:26:42.018885+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDGNTVAN7HQ2RQB6","created_at":"2026-07-05T09:26:42.018885+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDGNTVAN","created_at":"2026-07-05T09:26:42.018885+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31603","citing_title":"Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2505.11334","citing_title":"MARRS: Masked Autoregressive Unit-based Reaction Synthesis","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01099","citing_title":"Geometry-aware 4D Video Generation for Robot Manipulation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18678","citing_title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17248","citing_title":"Image-to-Video Diffusion: From Foundations to Open Frontiers","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18678","citing_title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23709","citing_title":"Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25161","citing_title":"Rolling Forcing: Autoregressive Long Video Diffusion in Real Time","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2602.07775","citing_title":"Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15564","citing_title":"Show-o2: Improved Native Unified Multimodal Models","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2506.08009","citing_title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2501.03575","citing_title":"Cosmos World Foundation Model Platform for Physical AI","ref_index":124,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07209","citing_title":"INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SDGNTVAN7HQ2RQB634BV25OGUY","json":"https://pith.science/pith/SDGNTVAN7HQ2RQB634BV25OGUY.json","graph_json":"https://pith.science/api/pith-number/SDGNTVAN7HQ2RQB634BV25OGUY/graph.json","events_json":"https://pith.science/api/pith-number/SDGNTVAN7HQ2RQB634BV25OGUY/events.json","paper":"https://pith.science/paper/SDGNTVAN"},"agent_actions":{"view_html":"https://pith.science/pith/SDGNTVAN7HQ2RQB634BV25OGUY","download_json":"https://pith.science/pith/SDGNTVAN7HQ2RQB634BV25OGUY.json","view_paper":"https://pith.science/paper/SDGNTVAN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20280&json=true","fetch_graph":"https://pith.science/api/pith-number/SDGNTVAN7HQ2RQB634BV25OGUY/graph.json","fetch_events":"https://pith.science/api/pith-number/SDGNTVAN7HQ2RQB634BV25OGUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDGNTVAN7HQ2RQB634BV25OGUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDGNTVAN7HQ2RQB634BV25OGUY/action/storage_attestation","attest_author":"https://pith.science/pith/SDGNTVAN7HQ2RQB634BV25OGUY/action/author_attestation","sign_citation":"https://pith.science/pith/SDGNTVAN7HQ2RQB634BV25OGUY/action/citation_signature","submit_replication":"https://pith.science/pith/SDGNTVAN7HQ2RQB634BV25OGUY/action/replication_record"}},"created_at":"2026-07-05T09:26:42.018885+00:00","updated_at":"2026-07-05T09:26:42.018885+00:00"}