{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WAVMSGKTPJKJJY5HU5JDTG7UGT","short_pith_number":"pith:WAVMSGKT","schema_version":"1.0","canonical_sha256":"b02ac919537a5494e3a7a752399bf434f470f8c6b603f2e0d1e39a3e8e5201c1","source":{"kind":"arxiv","id":"2207.09786","version":1},"attestation_state":"computed","paper":{"title":"Non-Uniform Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carola-Bibiane Sch\\\"onlieb, Christian Etmann, Georgios Batzolis, Jan Stanczuk","submitted_at":"2022-07-20T09:59:28Z","abstract_excerpt":"Diffusion models have emerged as one of the most promising frameworks for deep generative modeling. In this work, we explore the potential of non-uniform diffusion models. We show that non-uniform diffusion leads to multi-scale diffusion models which have similar structure to this of multi-scale normalizing flows. We experimentally find that in the same or less training time, the multi-scale diffusion model achieves better FID score than the standard uniform diffusion model. More importantly, it generates samples $4.4$ times faster in $128\\times 128$ resolution. The speed-up is expected to be "},"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":"2207.09786","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-20T09:59:28Z","cross_cats_sorted":[],"title_canon_sha256":"3c79d775b3b09e3488baa33f63fa69dab48a27d7e63b415201e280a790334851","abstract_canon_sha256":"597e8e41fd1050407434f65c14f9d7d0cff28c5713c755f1bc542048148be734"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:42:01.843691Z","signature_b64":"H2nITaZgXM97gT57y70L99JwtB+lt1m2WV/LxRNq5Bu+nPJj7FwE05Nl/4XNFZnUk6hRDUXA55ztahdLOUl4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b02ac919537a5494e3a7a752399bf434f470f8c6b603f2e0d1e39a3e8e5201c1","last_reissued_at":"2026-07-05T04:42:01.843230Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:42:01.843230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-Uniform Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carola-Bibiane Sch\\\"onlieb, Christian Etmann, Georgios Batzolis, Jan Stanczuk","submitted_at":"2022-07-20T09:59:28Z","abstract_excerpt":"Diffusion models have emerged as one of the most promising frameworks for deep generative modeling. In this work, we explore the potential of non-uniform diffusion models. We show that non-uniform diffusion leads to multi-scale diffusion models which have similar structure to this of multi-scale normalizing flows. We experimentally find that in the same or less training time, the multi-scale diffusion model achieves better FID score than the standard uniform diffusion model. More importantly, it generates samples $4.4$ times faster in $128\\times 128$ resolution. The speed-up is expected to be "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.09786","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/2207.09786/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":"2207.09786","created_at":"2026-07-05T04:42:01.843292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.09786v1","created_at":"2026-07-05T04:42:01.843292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.09786","created_at":"2026-07-05T04:42:01.843292+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAVMSGKTPJKJ","created_at":"2026-07-05T04:42:01.843292+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAVMSGKTPJKJJY5H","created_at":"2026-07-05T04:42:01.843292+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAVMSGKT","created_at":"2026-07-05T04:42:01.843292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06367","citing_title":"The Interplay of Data Structure and Imbalance in the Learning Dynamics of Diffusion Models","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WAVMSGKTPJKJJY5HU5JDTG7UGT","json":"https://pith.science/pith/WAVMSGKTPJKJJY5HU5JDTG7UGT.json","graph_json":"https://pith.science/api/pith-number/WAVMSGKTPJKJJY5HU5JDTG7UGT/graph.json","events_json":"https://pith.science/api/pith-number/WAVMSGKTPJKJJY5HU5JDTG7UGT/events.json","paper":"https://pith.science/paper/WAVMSGKT"},"agent_actions":{"view_html":"https://pith.science/pith/WAVMSGKTPJKJJY5HU5JDTG7UGT","download_json":"https://pith.science/pith/WAVMSGKTPJKJJY5HU5JDTG7UGT.json","view_paper":"https://pith.science/paper/WAVMSGKT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.09786&json=true","fetch_graph":"https://pith.science/api/pith-number/WAVMSGKTPJKJJY5HU5JDTG7UGT/graph.json","fetch_events":"https://pith.science/api/pith-number/WAVMSGKTPJKJJY5HU5JDTG7UGT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAVMSGKTPJKJJY5HU5JDTG7UGT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAVMSGKTPJKJJY5HU5JDTG7UGT/action/storage_attestation","attest_author":"https://pith.science/pith/WAVMSGKTPJKJJY5HU5JDTG7UGT/action/author_attestation","sign_citation":"https://pith.science/pith/WAVMSGKTPJKJJY5HU5JDTG7UGT/action/citation_signature","submit_replication":"https://pith.science/pith/WAVMSGKTPJKJJY5HU5JDTG7UGT/action/replication_record"}},"created_at":"2026-07-05T04:42:01.843292+00:00","updated_at":"2026-07-05T04:42:01.843292+00:00"}