{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W2RH7EMTV7YWLNNS6PIFKFUQUC","short_pith_number":"pith:W2RH7EMT","schema_version":"1.0","canonical_sha256":"b6a27f9193aff165b5b2f3d0551690a09570f327fd3a9e09d2db19aa80f4a414","source":{"kind":"arxiv","id":"2405.15506","version":4},"attestation_state":"computed","paper":{"title":"Learning to Discretize Denoising Diffusion ODEs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anji Liu, Guy Van den Broeck, Hoang Trung-Dung, Mathias Niepert, Vinh Tong","submitted_at":"2024-05-24T12:51:23Z","abstract_excerpt":"Diffusion Probabilistic Models (DPMs) are generative models showing competitive performance in various domains, including image synthesis and 3D point cloud generation. Sampling from pre-trained DPMs involves multiple neural function evaluations (NFEs) to transform Gaussian noise samples into images, resulting in higher computational costs compared to single-step generative models such as GANs or VAEs. Therefore, reducing the number of NFEs while preserving generation quality is crucial. To address this, we propose LD3, a lightweight framework designed to learn the optimal time discretization "},"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":"2405.15506","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T12:51:23Z","cross_cats_sorted":[],"title_canon_sha256":"413768653b5a536dbd577fd27e8f3bda657961f752dc85a88e142a1a4a15a6c8","abstract_canon_sha256":"8ece1291294727123dc54e0271b03b9c29c0f01e1d971175bc40d327805b6dba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:33.099989Z","signature_b64":"FpXrrA9wBO4giV66NByQyZMJHQhsrQ3/AVQWZKOwMF87A8H03kpDGnVYVr3Be3fZgtYNGmphkXsi3Ka4P6xCAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6a27f9193aff165b5b2f3d0551690a09570f327fd3a9e09d2db19aa80f4a414","last_reissued_at":"2026-07-05T11:05:33.099549Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:33.099549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Discretize Denoising Diffusion ODEs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anji Liu, Guy Van den Broeck, Hoang Trung-Dung, Mathias Niepert, Vinh Tong","submitted_at":"2024-05-24T12:51:23Z","abstract_excerpt":"Diffusion Probabilistic Models (DPMs) are generative models showing competitive performance in various domains, including image synthesis and 3D point cloud generation. Sampling from pre-trained DPMs involves multiple neural function evaluations (NFEs) to transform Gaussian noise samples into images, resulting in higher computational costs compared to single-step generative models such as GANs or VAEs. Therefore, reducing the number of NFEs while preserving generation quality is crucial. To address this, we propose LD3, a lightweight framework designed to learn the optimal time discretization "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15506","kind":"arxiv","version":4},"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/2405.15506/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":"2405.15506","created_at":"2026-07-05T11:05:33.099610+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15506v4","created_at":"2026-07-05T11:05:33.099610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15506","created_at":"2026-07-05T11:05:33.099610+00:00"},{"alias_kind":"pith_short_12","alias_value":"W2RH7EMTV7YW","created_at":"2026-07-05T11:05:33.099610+00:00"},{"alias_kind":"pith_short_16","alias_value":"W2RH7EMTV7YWLNNS","created_at":"2026-07-05T11:05:33.099610+00:00"},{"alias_kind":"pith_short_8","alias_value":"W2RH7EMT","created_at":"2026-07-05T11:05:33.099610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13496","citing_title":"Budget-Constrained Step-Level Diffusion Caching","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2602.07715","citing_title":"Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18905","citing_title":"Stability and Discretization Error of State Space Model Neural Operators","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W2RH7EMTV7YWLNNS6PIFKFUQUC","json":"https://pith.science/pith/W2RH7EMTV7YWLNNS6PIFKFUQUC.json","graph_json":"https://pith.science/api/pith-number/W2RH7EMTV7YWLNNS6PIFKFUQUC/graph.json","events_json":"https://pith.science/api/pith-number/W2RH7EMTV7YWLNNS6PIFKFUQUC/events.json","paper":"https://pith.science/paper/W2RH7EMT"},"agent_actions":{"view_html":"https://pith.science/pith/W2RH7EMTV7YWLNNS6PIFKFUQUC","download_json":"https://pith.science/pith/W2RH7EMTV7YWLNNS6PIFKFUQUC.json","view_paper":"https://pith.science/paper/W2RH7EMT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15506&json=true","fetch_graph":"https://pith.science/api/pith-number/W2RH7EMTV7YWLNNS6PIFKFUQUC/graph.json","fetch_events":"https://pith.science/api/pith-number/W2RH7EMTV7YWLNNS6PIFKFUQUC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W2RH7EMTV7YWLNNS6PIFKFUQUC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W2RH7EMTV7YWLNNS6PIFKFUQUC/action/storage_attestation","attest_author":"https://pith.science/pith/W2RH7EMTV7YWLNNS6PIFKFUQUC/action/author_attestation","sign_citation":"https://pith.science/pith/W2RH7EMTV7YWLNNS6PIFKFUQUC/action/citation_signature","submit_replication":"https://pith.science/pith/W2RH7EMTV7YWLNNS6PIFKFUQUC/action/replication_record"}},"created_at":"2026-07-05T11:05:33.099610+00:00","updated_at":"2026-07-05T11:05:33.099610+00:00"}