{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ORP25M3Y333AUFDDI5F6MZY4VN","short_pith_number":"pith:ORP25M3Y","schema_version":"1.0","canonical_sha256":"745faeb378def60a1463474be6671cab50b1406a4c67b0f5328f1c3313b93ce9","source":{"kind":"arxiv","id":"2402.03666","version":6},"attestation_state":"computed","paper":{"title":"QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoxuan Wang, Junchi Yan, Junyi Wu, Yan Yan, Yuzhang Shang, Zhihang Yuan","submitted_at":"2024-02-06T03:39:44Z","abstract_excerpt":"The practical deployment of diffusion models is still hindered by the high memory and computational overhead. Although quantization paves a way for model compression and acceleration, existing methods face challenges in achieving low-bit quantization efficiently. In this paper, we identify imbalanced activation distributions as a primary source of quantization difficulty, and propose to adjust these distributions through weight finetuning to be more quantization-friendly. We provide both theoretical and empirical evidence supporting finetuning as a practical and reliable solution. Building on "},"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":"2402.03666","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T03:39:44Z","cross_cats_sorted":[],"title_canon_sha256":"3368083efdfb4f49abf8fe8e2204e9401ea6105416ea6d3d6f0a729079362137","abstract_canon_sha256":"458d209da14eb6cd4ad5f8acb4d2957460f3f3327335a71ec6702f5e38791dc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:08.197008Z","signature_b64":"25oY3M0fPhfnrmdbHjDnd90763q0xEbUEtqimCR3JgXGk5ZL9IMkCBihGeLKPZRXcfsAn78KozqZKltJ0b9EBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"745faeb378def60a1463474be6671cab50b1406a4c67b0f5328f1c3313b93ce9","last_reissued_at":"2026-07-05T11:37:08.196522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:08.196522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoxuan Wang, Junchi Yan, Junyi Wu, Yan Yan, Yuzhang Shang, Zhihang Yuan","submitted_at":"2024-02-06T03:39:44Z","abstract_excerpt":"The practical deployment of diffusion models is still hindered by the high memory and computational overhead. Although quantization paves a way for model compression and acceleration, existing methods face challenges in achieving low-bit quantization efficiently. In this paper, we identify imbalanced activation distributions as a primary source of quantization difficulty, and propose to adjust these distributions through weight finetuning to be more quantization-friendly. We provide both theoretical and empirical evidence supporting finetuning as a practical and reliable solution. Building on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03666","kind":"arxiv","version":6},"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/2402.03666/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":"2402.03666","created_at":"2026-07-05T11:37:08.196580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03666v6","created_at":"2026-07-05T11:37:08.196580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03666","created_at":"2026-07-05T11:37:08.196580+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORP25M3Y333A","created_at":"2026-07-05T11:37:08.196580+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORP25M3Y333AUFDD","created_at":"2026-07-05T11:37:08.196580+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORP25M3Y","created_at":"2026-07-05T11:37:08.196580+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01624","citing_title":"Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ORP25M3Y333AUFDDI5F6MZY4VN","json":"https://pith.science/pith/ORP25M3Y333AUFDDI5F6MZY4VN.json","graph_json":"https://pith.science/api/pith-number/ORP25M3Y333AUFDDI5F6MZY4VN/graph.json","events_json":"https://pith.science/api/pith-number/ORP25M3Y333AUFDDI5F6MZY4VN/events.json","paper":"https://pith.science/paper/ORP25M3Y"},"agent_actions":{"view_html":"https://pith.science/pith/ORP25M3Y333AUFDDI5F6MZY4VN","download_json":"https://pith.science/pith/ORP25M3Y333AUFDDI5F6MZY4VN.json","view_paper":"https://pith.science/paper/ORP25M3Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03666&json=true","fetch_graph":"https://pith.science/api/pith-number/ORP25M3Y333AUFDDI5F6MZY4VN/graph.json","fetch_events":"https://pith.science/api/pith-number/ORP25M3Y333AUFDDI5F6MZY4VN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORP25M3Y333AUFDDI5F6MZY4VN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORP25M3Y333AUFDDI5F6MZY4VN/action/storage_attestation","attest_author":"https://pith.science/pith/ORP25M3Y333AUFDDI5F6MZY4VN/action/author_attestation","sign_citation":"https://pith.science/pith/ORP25M3Y333AUFDDI5F6MZY4VN/action/citation_signature","submit_replication":"https://pith.science/pith/ORP25M3Y333AUFDDI5F6MZY4VN/action/replication_record"}},"created_at":"2026-07-05T11:37:08.196580+00:00","updated_at":"2026-07-05T11:37:08.196580+00:00"}