{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7GIAVSUBJL2YCHNHUL2GQKCCDD","short_pith_number":"pith:7GIAVSUB","schema_version":"1.0","canonical_sha256":"f9900aca814af5811da7a2f468284218c8d67d55a68456486c7f2d242a4dce3d","source":{"kind":"arxiv","id":"2607.06631","version":1},"attestation_state":"computed","paper":{"title":"Dynamic-in-Few-Step: Unifying Dynamic Computation and Few-Step Distillation for Efficient Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fajie Yuan, Shanyan Guan, Siyue Yao, Wei Li, Yu Cheng, Zhongang Qi","submitted_at":"2026-07-07T13:14:33Z","abstract_excerpt":"Video Diffusion Models (VDMs) have demonstrated superior generation quality but suffer from prohibitive computational costs. While recent few-step distillation techniques significantly accelerate inference, they typically enforce a static model architecture across all denoising stages, ignoring the varying computational demands inherent to different noise levels. In this work, we propose a novel post-training acceleration framework that exploits this redundancy by integrating dynamic structural sparsification directly into the distillation process. Unlike conventional post-hoc compression appl"},"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":"2607.06631","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T13:14:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"855d7ac3a9c3eede7bb0b0123acae22f4ddf0ea62dd882ad7a2c4e52a6a3fbfa","abstract_canon_sha256":"04faaedf5487ab7763a55d8865dac146a44993a374c9cc2e9ef29f1c39568a86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T00:19:21.035779Z","signature_b64":"4y9+f4EeCRFmv+41h9HUEzbBsALGRmcwIUyL2IdbHErx2AR5JgDlWNkKgTB3iS+7wMDycvQPNOkm0jA+ZVZ2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9900aca814af5811da7a2f468284218c8d67d55a68456486c7f2d242a4dce3d","last_reissued_at":"2026-07-09T00:19:21.035032Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T00:19:21.035032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic-in-Few-Step: Unifying Dynamic Computation and Few-Step Distillation for Efficient Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fajie Yuan, Shanyan Guan, Siyue Yao, Wei Li, Yu Cheng, Zhongang Qi","submitted_at":"2026-07-07T13:14:33Z","abstract_excerpt":"Video Diffusion Models (VDMs) have demonstrated superior generation quality but suffer from prohibitive computational costs. While recent few-step distillation techniques significantly accelerate inference, they typically enforce a static model architecture across all denoising stages, ignoring the varying computational demands inherent to different noise levels. In this work, we propose a novel post-training acceleration framework that exploits this redundancy by integrating dynamic structural sparsification directly into the distillation process. Unlike conventional post-hoc compression appl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06631","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/2607.06631/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":"2607.06631","created_at":"2026-07-09T00:19:21.035160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06631v1","created_at":"2026-07-09T00:19:21.035160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06631","created_at":"2026-07-09T00:19:21.035160+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GIAVSUBJL2Y","created_at":"2026-07-09T00:19:21.035160+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GIAVSUBJL2YCHNH","created_at":"2026-07-09T00:19:21.035160+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GIAVSUB","created_at":"2026-07-09T00:19:21.035160+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/7GIAVSUBJL2YCHNHUL2GQKCCDD","json":"https://pith.science/pith/7GIAVSUBJL2YCHNHUL2GQKCCDD.json","graph_json":"https://pith.science/api/pith-number/7GIAVSUBJL2YCHNHUL2GQKCCDD/graph.json","events_json":"https://pith.science/api/pith-number/7GIAVSUBJL2YCHNHUL2GQKCCDD/events.json","paper":"https://pith.science/paper/7GIAVSUB"},"agent_actions":{"view_html":"https://pith.science/pith/7GIAVSUBJL2YCHNHUL2GQKCCDD","download_json":"https://pith.science/pith/7GIAVSUBJL2YCHNHUL2GQKCCDD.json","view_paper":"https://pith.science/paper/7GIAVSUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06631&json=true","fetch_graph":"https://pith.science/api/pith-number/7GIAVSUBJL2YCHNHUL2GQKCCDD/graph.json","fetch_events":"https://pith.science/api/pith-number/7GIAVSUBJL2YCHNHUL2GQKCCDD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GIAVSUBJL2YCHNHUL2GQKCCDD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GIAVSUBJL2YCHNHUL2GQKCCDD/action/storage_attestation","attest_author":"https://pith.science/pith/7GIAVSUBJL2YCHNHUL2GQKCCDD/action/author_attestation","sign_citation":"https://pith.science/pith/7GIAVSUBJL2YCHNHUL2GQKCCDD/action/citation_signature","submit_replication":"https://pith.science/pith/7GIAVSUBJL2YCHNHUL2GQKCCDD/action/replication_record"}},"created_at":"2026-07-09T00:19:21.035160+00:00","updated_at":"2026-07-09T00:19:21.035160+00:00"}