{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MWA65GQFU22DWRPXRZHESB4EO6","short_pith_number":"pith:MWA65GQF","schema_version":"1.0","canonical_sha256":"6581ee9a05a6b43b45f78e4e49078477adfed4fd5ca72679fd9ced233c988cb0","source":{"kind":"arxiv","id":"2505.20789","version":3},"attestation_state":"computed","paper":{"title":"Integrating Intermediate Layer Optimization and Projected Gradient Descent for Solving Inverse Problems with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Wen Li, Yang Zheng, Zhaoqiang Liu","submitted_at":"2025-05-27T06:49:02Z","abstract_excerpt":"Inverse problems (IPs) involve reconstructing signals from noisy observations. Recently, diffusion models (DMs) have emerged as a powerful framework for solving IPs, achieving remarkable reconstruction performance. However, existing DM-based methods frequently encounter issues such as heavy computational demands and suboptimal convergence. In this work, building upon the idea of the recent work DMPlug, we propose two novel methods, DMILO and DMILO-PGD, to address these challenges. Our first method, DMILO, employs intermediate layer optimization (ILO) to alleviate the memory burden inherent in "},"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":"2505.20789","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T06:49:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"50956f8ec98d24915ad3f86b8c6c2bf0411b44cc3342367c33080f73064eda7b","abstract_canon_sha256":"436c142c3a633382dff1ec8db2f1624371e84f2425fda2a35fbd6a49a6901086"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:35.187192Z","signature_b64":"3jDNwpegIoD0uLU9JzI/81bFgsW6shOGqA5fkZrY0ujdAIl2qriNEtxlddQ9c4s99+qYvdYc1ucUvtPZYCt2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6581ee9a05a6b43b45f78e4e49078477adfed4fd5ca72679fd9ced233c988cb0","last_reissued_at":"2026-07-05T12:04:35.186665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:35.186665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Integrating Intermediate Layer Optimization and Projected Gradient Descent for Solving Inverse Problems with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Wen Li, Yang Zheng, Zhaoqiang Liu","submitted_at":"2025-05-27T06:49:02Z","abstract_excerpt":"Inverse problems (IPs) involve reconstructing signals from noisy observations. Recently, diffusion models (DMs) have emerged as a powerful framework for solving IPs, achieving remarkable reconstruction performance. However, existing DM-based methods frequently encounter issues such as heavy computational demands and suboptimal convergence. In this work, building upon the idea of the recent work DMPlug, we propose two novel methods, DMILO and DMILO-PGD, to address these challenges. Our first method, DMILO, employs intermediate layer optimization (ILO) to alleviate the memory burden inherent in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20789","kind":"arxiv","version":3},"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/2505.20789/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":"2505.20789","created_at":"2026-07-05T12:04:35.186722+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20789v3","created_at":"2026-07-05T12:04:35.186722+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20789","created_at":"2026-07-05T12:04:35.186722+00:00"},{"alias_kind":"pith_short_12","alias_value":"MWA65GQFU22D","created_at":"2026-07-05T12:04:35.186722+00:00"},{"alias_kind":"pith_short_16","alias_value":"MWA65GQFU22DWRPX","created_at":"2026-07-05T12:04:35.186722+00:00"},{"alias_kind":"pith_short_8","alias_value":"MWA65GQF","created_at":"2026-07-05T12:04:35.186722+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MWA65GQFU22DWRPXRZHESB4EO6","json":"https://pith.science/pith/MWA65GQFU22DWRPXRZHESB4EO6.json","graph_json":"https://pith.science/api/pith-number/MWA65GQFU22DWRPXRZHESB4EO6/graph.json","events_json":"https://pith.science/api/pith-number/MWA65GQFU22DWRPXRZHESB4EO6/events.json","paper":"https://pith.science/paper/MWA65GQF"},"agent_actions":{"view_html":"https://pith.science/pith/MWA65GQFU22DWRPXRZHESB4EO6","download_json":"https://pith.science/pith/MWA65GQFU22DWRPXRZHESB4EO6.json","view_paper":"https://pith.science/paper/MWA65GQF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20789&json=true","fetch_graph":"https://pith.science/api/pith-number/MWA65GQFU22DWRPXRZHESB4EO6/graph.json","fetch_events":"https://pith.science/api/pith-number/MWA65GQFU22DWRPXRZHESB4EO6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MWA65GQFU22DWRPXRZHESB4EO6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MWA65GQFU22DWRPXRZHESB4EO6/action/storage_attestation","attest_author":"https://pith.science/pith/MWA65GQFU22DWRPXRZHESB4EO6/action/author_attestation","sign_citation":"https://pith.science/pith/MWA65GQFU22DWRPXRZHESB4EO6/action/citation_signature","submit_replication":"https://pith.science/pith/MWA65GQFU22DWRPXRZHESB4EO6/action/replication_record"}},"created_at":"2026-07-05T12:04:35.186722+00:00","updated_at":"2026-07-05T12:04:35.186722+00:00"}