{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NDLHEM6YWX2SWTSMXAWSVV2MCR","short_pith_number":"pith:NDLHEM6Y","schema_version":"1.0","canonical_sha256":"68d67233d8b5f52b4e4cb82d2ad74c146d01e65d1dfde502dd63567ab50452b1","source":{"kind":"arxiv","id":"2405.17401","version":1},"attestation_state":"computed","paper":{"title":"RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Kumar, Constantine Caramanis, Litu Rout, Nataniel Ruiz, Sanjay Shakkottai, Wen-Sheng Chu, Yujia Chen","submitted_at":"2024-05-27T17:51:08Z","abstract_excerpt":"We propose Reference-Based Modulation (RB-Modulation), a new plug-and-play solution for training-free personalization of diffusion models. Existing training-free approaches exhibit difficulties in (a) style extraction from reference images in the absence of additional style or content text descriptions, (b) unwanted content leakage from reference style images, and (c) effective composition of style and content. RB-Modulation is built on a novel stochastic optimal controller where a style descriptor encodes the desired attributes through a terminal cost. The resulting drift not only overcomes t"},"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":"2405.17401","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T17:51:08Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"429591d93d89cc88f5551ecff2fa65674d4b265535c70ed707723fe225f76013","abstract_canon_sha256":"d5916eaa66e5a9d8d1c869c93d08a7ee4f3ecc3aa80e4cef975beee003e070e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:43.959214Z","signature_b64":"uwSnLCW4rtnAl/LI/LDCYNtS9eW3O7gH92h6p2rmsNJKhqEfnbgjxIy8xqQgVYH6zMgryVumMyOp8hjTIPDaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68d67233d8b5f52b4e4cb82d2ad74c146d01e65d1dfde502dd63567ab50452b1","last_reissued_at":"2026-07-05T08:23:43.958724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:43.958724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Kumar, Constantine Caramanis, Litu Rout, Nataniel Ruiz, Sanjay Shakkottai, Wen-Sheng Chu, Yujia Chen","submitted_at":"2024-05-27T17:51:08Z","abstract_excerpt":"We propose Reference-Based Modulation (RB-Modulation), a new plug-and-play solution for training-free personalization of diffusion models. Existing training-free approaches exhibit difficulties in (a) style extraction from reference images in the absence of additional style or content text descriptions, (b) unwanted content leakage from reference style images, and (c) effective composition of style and content. RB-Modulation is built on a novel stochastic optimal controller where a style descriptor encodes the desired attributes through a terminal cost. The resulting drift not only overcomes t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17401","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/2405.17401/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":"2405.17401","created_at":"2026-07-05T08:23:43.958784+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17401v1","created_at":"2026-07-05T08:23:43.958784+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17401","created_at":"2026-07-05T08:23:43.958784+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDLHEM6YWX2S","created_at":"2026-07-05T08:23:43.958784+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDLHEM6YWX2SWTSM","created_at":"2026-07-05T08:23:43.958784+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDLHEM6Y","created_at":"2026-07-05T08:23:43.958784+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27147","citing_title":"How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28785","citing_title":"Stochastic Optimal Control Sampling for Diffusion Inverse Problems","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2503.19034","citing_title":"Color Conditional Generation with Sliced Wasserstein Guidance","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27147","citing_title":"How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25845","citing_title":"Training-Free Reward-Guided Image Editing via Trajectory Optimal Control","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27147","citing_title":"How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05183","citing_title":"OrthoFuse: Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion Models","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NDLHEM6YWX2SWTSMXAWSVV2MCR","json":"https://pith.science/pith/NDLHEM6YWX2SWTSMXAWSVV2MCR.json","graph_json":"https://pith.science/api/pith-number/NDLHEM6YWX2SWTSMXAWSVV2MCR/graph.json","events_json":"https://pith.science/api/pith-number/NDLHEM6YWX2SWTSMXAWSVV2MCR/events.json","paper":"https://pith.science/paper/NDLHEM6Y"},"agent_actions":{"view_html":"https://pith.science/pith/NDLHEM6YWX2SWTSMXAWSVV2MCR","download_json":"https://pith.science/pith/NDLHEM6YWX2SWTSMXAWSVV2MCR.json","view_paper":"https://pith.science/paper/NDLHEM6Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17401&json=true","fetch_graph":"https://pith.science/api/pith-number/NDLHEM6YWX2SWTSMXAWSVV2MCR/graph.json","fetch_events":"https://pith.science/api/pith-number/NDLHEM6YWX2SWTSMXAWSVV2MCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDLHEM6YWX2SWTSMXAWSVV2MCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDLHEM6YWX2SWTSMXAWSVV2MCR/action/storage_attestation","attest_author":"https://pith.science/pith/NDLHEM6YWX2SWTSMXAWSVV2MCR/action/author_attestation","sign_citation":"https://pith.science/pith/NDLHEM6YWX2SWTSMXAWSVV2MCR/action/citation_signature","submit_replication":"https://pith.science/pith/NDLHEM6YWX2SWTSMXAWSVV2MCR/action/replication_record"}},"created_at":"2026-07-05T08:23:43.958784+00:00","updated_at":"2026-07-05T08:23:43.958784+00:00"}