{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CFUQLVASMVBT3QGXOYPVJHZZKN","short_pith_number":"pith:CFUQLVAS","schema_version":"1.0","canonical_sha256":"116905d41265433dc0d7761f549f395379034dbac686acdf805dd422be912bfa","source":{"kind":"arxiv","id":"2410.20502","version":3},"attestation_state":"computed","paper":{"title":"ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Furu Wei, Hefei Ling, Jeongsoo Choi, Jinyu Li, Lingwei Meng, Long Zhou, Shujie Hu, Shujie Liu, Xun Guo, Zongyi Li","submitted_at":"2024-10-27T16:28:28Z","abstract_excerpt":"Text-to-video models have recently undergone rapid and substantial advancements. Nevertheless, due to limitations in data and computational resources, achieving efficient generation of long videos with rich motion dynamics remains a significant challenge. To generate high-quality, dynamic, and temporally consistent long videos, this paper presents ARLON, a novel framework that boosts diffusion Transformers with autoregressive models for long video generation, by integrating the coarse spatial and long-range temporal information provided by the AR model to guide the DiT model. Specifically, ARL"},"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":"2410.20502","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-27T16:28:28Z","cross_cats_sorted":[],"title_canon_sha256":"0969678ebb21a44ae6dae83a47b6ba76da05421ad94de068b167e569dcbbf59d","abstract_canon_sha256":"3aaa921c36c10a45a2a9b8ae88af12426992976cfd098ed789ca97a21e342053"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:10.553174Z","signature_b64":"pnDLlFbOqA8cVy89M858Uak38i+cbpQah6PKqBMN+eRFUYpmZz/zcjy196DG8UGOPUyq56CPxwoQzHmZyG8yDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"116905d41265433dc0d7761f549f395379034dbac686acdf805dd422be912bfa","last_reissued_at":"2026-07-05T10:49:10.552701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:10.552701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Furu Wei, Hefei Ling, Jeongsoo Choi, Jinyu Li, Lingwei Meng, Long Zhou, Shujie Hu, Shujie Liu, Xun Guo, Zongyi Li","submitted_at":"2024-10-27T16:28:28Z","abstract_excerpt":"Text-to-video models have recently undergone rapid and substantial advancements. Nevertheless, due to limitations in data and computational resources, achieving efficient generation of long videos with rich motion dynamics remains a significant challenge. To generate high-quality, dynamic, and temporally consistent long videos, this paper presents ARLON, a novel framework that boosts diffusion Transformers with autoregressive models for long video generation, by integrating the coarse spatial and long-range temporal information provided by the AR model to guide the DiT model. Specifically, ARL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20502","kind":"arxiv","version":3},"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/2410.20502/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":"2410.20502","created_at":"2026-07-05T10:49:10.552759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20502v3","created_at":"2026-07-05T10:49:10.552759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20502","created_at":"2026-07-05T10:49:10.552759+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFUQLVASMVBT","created_at":"2026-07-05T10:49:10.552759+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFUQLVASMVBT3QGX","created_at":"2026-07-05T10:49:10.552759+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFUQLVAS","created_at":"2026-07-05T10:49:10.552759+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07967","citing_title":"DisCo: World Models with Discrete Camera Motion Control","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31603","citing_title":"Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01099","citing_title":"Geometry-aware 4D Video Generation for Robot Manipulation","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2505.21996","citing_title":"VRAG: Learning World Models for Interactive Video Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25161","citing_title":"Rolling Forcing: Autoregressive Long Video Diffusion in Real Time","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18348","citing_title":"AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15911","citing_title":"Efficient Video Diffusion Models: Advancements and Challenges","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04461","citing_title":"Stream-T1: Test-Time Scaling for Streaming Video Generation","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CFUQLVASMVBT3QGXOYPVJHZZKN","json":"https://pith.science/pith/CFUQLVASMVBT3QGXOYPVJHZZKN.json","graph_json":"https://pith.science/api/pith-number/CFUQLVASMVBT3QGXOYPVJHZZKN/graph.json","events_json":"https://pith.science/api/pith-number/CFUQLVASMVBT3QGXOYPVJHZZKN/events.json","paper":"https://pith.science/paper/CFUQLVAS"},"agent_actions":{"view_html":"https://pith.science/pith/CFUQLVASMVBT3QGXOYPVJHZZKN","download_json":"https://pith.science/pith/CFUQLVASMVBT3QGXOYPVJHZZKN.json","view_paper":"https://pith.science/paper/CFUQLVAS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20502&json=true","fetch_graph":"https://pith.science/api/pith-number/CFUQLVASMVBT3QGXOYPVJHZZKN/graph.json","fetch_events":"https://pith.science/api/pith-number/CFUQLVASMVBT3QGXOYPVJHZZKN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFUQLVASMVBT3QGXOYPVJHZZKN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFUQLVASMVBT3QGXOYPVJHZZKN/action/storage_attestation","attest_author":"https://pith.science/pith/CFUQLVASMVBT3QGXOYPVJHZZKN/action/author_attestation","sign_citation":"https://pith.science/pith/CFUQLVASMVBT3QGXOYPVJHZZKN/action/citation_signature","submit_replication":"https://pith.science/pith/CFUQLVASMVBT3QGXOYPVJHZZKN/action/replication_record"}},"created_at":"2026-07-05T10:49:10.552759+00:00","updated_at":"2026-07-05T10:49:10.552759+00:00"}