{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WGPYIES3C43GJ2S4CWJPQ26JYF","short_pith_number":"pith:WGPYIES3","schema_version":"1.0","canonical_sha256":"b19f84125b173664ea5c1592f86bc9c17f06760f9cda019aa1ccc8b83cdf8c41","source":{"kind":"arxiv","id":"2404.00879","version":1},"attestation_state":"computed","paper":{"title":"Model-Agnostic Human Preference Inversion in Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jeeyung Kim, Qiang Qiu, Ze Wang","submitted_at":"2024-04-01T03:18:12Z","abstract_excerpt":"Efficient text-to-image generation remains a challenging task due to the high computational costs associated with the multi-step sampling in diffusion models. Although distillation of pre-trained diffusion models has been successful in reducing sampling steps, low-step image generation often falls short in terms of quality. In this study, we propose a novel sampling design to achieve high-quality one-step image generation aligning with human preferences, particularly focusing on exploring the impact of the prior noise distribution. Our approach, Prompt Adaptive Human Preference Inversion (PAHI"},"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":"2404.00879","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T03:18:12Z","cross_cats_sorted":[],"title_canon_sha256":"0e6903b852e3e2ace9272e1a4c2d5fa1499609a48fbca07bc1b6836b305c0d81","abstract_canon_sha256":"18f2e9e077d5a64c9f37fd0e02e4c1bed383c515dcd8218338ff6224317a3f72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:57.878192Z","signature_b64":"Y4xq5cU+p4oVcgKjsDKChMAbdomu+/m4XzahjrxbmS3yu8VZO+/AEasxdaoB2np7KkdjWAcK3KU7Gs7tTHalAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b19f84125b173664ea5c1592f86bc9c17f06760f9cda019aa1ccc8b83cdf8c41","last_reissued_at":"2026-07-05T08:02:57.877854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:57.877854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Agnostic Human Preference Inversion in Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jeeyung Kim, Qiang Qiu, Ze Wang","submitted_at":"2024-04-01T03:18:12Z","abstract_excerpt":"Efficient text-to-image generation remains a challenging task due to the high computational costs associated with the multi-step sampling in diffusion models. Although distillation of pre-trained diffusion models has been successful in reducing sampling steps, low-step image generation often falls short in terms of quality. In this study, we propose a novel sampling design to achieve high-quality one-step image generation aligning with human preferences, particularly focusing on exploring the impact of the prior noise distribution. Our approach, Prompt Adaptive Human Preference Inversion (PAHI"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00879","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/2404.00879/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":"2404.00879","created_at":"2026-07-05T08:02:57.877902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00879v1","created_at":"2026-07-05T08:02:57.877902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00879","created_at":"2026-07-05T08:02:57.877902+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGPYIES3C43G","created_at":"2026-07-05T08:02:57.877902+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGPYIES3C43GJ2S4","created_at":"2026-07-05T08:02:57.877902+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGPYIES3","created_at":"2026-07-05T08:02:57.877902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02521","citing_title":"Drifting Preference Optimization for One-Step Generative Models","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WGPYIES3C43GJ2S4CWJPQ26JYF","json":"https://pith.science/pith/WGPYIES3C43GJ2S4CWJPQ26JYF.json","graph_json":"https://pith.science/api/pith-number/WGPYIES3C43GJ2S4CWJPQ26JYF/graph.json","events_json":"https://pith.science/api/pith-number/WGPYIES3C43GJ2S4CWJPQ26JYF/events.json","paper":"https://pith.science/paper/WGPYIES3"},"agent_actions":{"view_html":"https://pith.science/pith/WGPYIES3C43GJ2S4CWJPQ26JYF","download_json":"https://pith.science/pith/WGPYIES3C43GJ2S4CWJPQ26JYF.json","view_paper":"https://pith.science/paper/WGPYIES3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00879&json=true","fetch_graph":"https://pith.science/api/pith-number/WGPYIES3C43GJ2S4CWJPQ26JYF/graph.json","fetch_events":"https://pith.science/api/pith-number/WGPYIES3C43GJ2S4CWJPQ26JYF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGPYIES3C43GJ2S4CWJPQ26JYF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGPYIES3C43GJ2S4CWJPQ26JYF/action/storage_attestation","attest_author":"https://pith.science/pith/WGPYIES3C43GJ2S4CWJPQ26JYF/action/author_attestation","sign_citation":"https://pith.science/pith/WGPYIES3C43GJ2S4CWJPQ26JYF/action/citation_signature","submit_replication":"https://pith.science/pith/WGPYIES3C43GJ2S4CWJPQ26JYF/action/replication_record"}},"created_at":"2026-07-05T08:02:57.877902+00:00","updated_at":"2026-07-05T08:02:57.877902+00:00"}