{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZFIOE272OD3AWAE77EAFRBXNSK","short_pith_number":"pith:ZFIOE272","schema_version":"1.0","canonical_sha256":"c950e26bfa70f60b009ff9005886ed92ab16ecdab6e7e9941409f1cad9f16af3","source":{"kind":"arxiv","id":"2410.09873","version":1},"attestation_state":"computed","paper":{"title":"Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Botian Shi, Bo Zhang, Hancheng Ye, Jiakang Yuan, Junchi Yan, Renqiu Xia, Tao Chen, Xiangchao Yan","submitted_at":"2024-10-13T15:19:18Z","abstract_excerpt":"Diffusion models have recently achieved great success in the synthesis of high-quality images and videos. However, the existing denoising techniques in diffusion models are commonly based on step-by-step noise predictions, which suffers from high computation cost, resulting in a prohibitive latency for interactive applications. In this paper, we propose AdaptiveDiffusion to relieve this bottleneck by adaptively reducing the noise prediction steps during the denoising process. Our method considers the potential of skipping as many noise prediction steps as possible while keeping the final denoi"},"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":"2410.09873","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-13T15:19:18Z","cross_cats_sorted":[],"title_canon_sha256":"cab48a6b57016e005ee5b6282928b7d6bc833776f9541a895039984186e83842","abstract_canon_sha256":"741118a346097076ed87e59f27245ff5cdbad29c748018c7eeacd02074dd5bd3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:07.382326Z","signature_b64":"XYUzY2vV6w7SMePcrEuWq+iQPgqY41ZBUR8FqxO6Q4Oe/XG5ADkGU4QzSxJLc1IkIYdUrcemCMDmlmw4XYIPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c950e26bfa70f60b009ff9005886ed92ab16ecdab6e7e9941409f1cad9f16af3","last_reissued_at":"2026-07-05T09:20:07.381871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:07.381871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Botian Shi, Bo Zhang, Hancheng Ye, Jiakang Yuan, Junchi Yan, Renqiu Xia, Tao Chen, Xiangchao Yan","submitted_at":"2024-10-13T15:19:18Z","abstract_excerpt":"Diffusion models have recently achieved great success in the synthesis of high-quality images and videos. However, the existing denoising techniques in diffusion models are commonly based on step-by-step noise predictions, which suffers from high computation cost, resulting in a prohibitive latency for interactive applications. In this paper, we propose AdaptiveDiffusion to relieve this bottleneck by adaptively reducing the noise prediction steps during the denoising process. Our method considers the potential of skipping as many noise prediction steps as possible while keeping the final denoi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09873","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/2410.09873/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":"2410.09873","created_at":"2026-07-05T09:20:07.381928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09873v1","created_at":"2026-07-05T09:20:07.381928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09873","created_at":"2026-07-05T09:20:07.381928+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFIOE272OD3A","created_at":"2026-07-05T09:20:07.381928+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFIOE272OD3AWAE7","created_at":"2026-07-05T09:20:07.381928+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFIOE272","created_at":"2026-07-05T09:20:07.381928+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17135","citing_title":"SADA: Stability-guided Adaptive Diffusion Acceleration","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZFIOE272OD3AWAE77EAFRBXNSK","json":"https://pith.science/pith/ZFIOE272OD3AWAE77EAFRBXNSK.json","graph_json":"https://pith.science/api/pith-number/ZFIOE272OD3AWAE77EAFRBXNSK/graph.json","events_json":"https://pith.science/api/pith-number/ZFIOE272OD3AWAE77EAFRBXNSK/events.json","paper":"https://pith.science/paper/ZFIOE272"},"agent_actions":{"view_html":"https://pith.science/pith/ZFIOE272OD3AWAE77EAFRBXNSK","download_json":"https://pith.science/pith/ZFIOE272OD3AWAE77EAFRBXNSK.json","view_paper":"https://pith.science/paper/ZFIOE272","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09873&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFIOE272OD3AWAE77EAFRBXNSK/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFIOE272OD3AWAE77EAFRBXNSK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFIOE272OD3AWAE77EAFRBXNSK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFIOE272OD3AWAE77EAFRBXNSK/action/storage_attestation","attest_author":"https://pith.science/pith/ZFIOE272OD3AWAE77EAFRBXNSK/action/author_attestation","sign_citation":"https://pith.science/pith/ZFIOE272OD3AWAE77EAFRBXNSK/action/citation_signature","submit_replication":"https://pith.science/pith/ZFIOE272OD3AWAE77EAFRBXNSK/action/replication_record"}},"created_at":"2026-07-05T09:20:07.381928+00:00","updated_at":"2026-07-05T09:20:07.381928+00:00"}