{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3VVRY2EIUH47UJOXXYQTM4XGXF","short_pith_number":"pith:3VVRY2EI","schema_version":"1.0","canonical_sha256":"dd6b1c6888a1f9fa25d7be213672e6b967b8e4b74a32e026eef4797d5f7b0bf0","source":{"kind":"arxiv","id":"2405.18897","version":2},"attestation_state":"computed","paper":{"title":"MLAE: Masked LoRA Experts for Visual Parameter-Efficient Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangjing Yang, Huahui Yi, Junjie Wang, Qicheng Lao, Wentao Chen, Xiaohu Wu, Zhouchen Lin","submitted_at":"2024-05-29T08:57:23Z","abstract_excerpt":"In response to the challenges posed by the extensive parameter updates required for full fine-tuning of large-scale pre-trained models, parameter-efficient fine-tuning (PEFT) methods, exemplified by Low-Rank Adaptation (LoRA), have emerged. LoRA simplifies the fine-tuning process but may still struggle with a certain level of redundancy in low-rank matrices and limited effectiveness from merely increasing their rank. To address these issues, a natural idea is to enhance the independence and diversity of the learning process for the low-rank matrices. Therefore, we propose Masked LoRA Experts ("},"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":"2405.18897","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T08:57:23Z","cross_cats_sorted":[],"title_canon_sha256":"c88ec6aeb56c9b75ca28be6c71d17dc671d2a026bfa9ed15ba22cd5ad166f25b","abstract_canon_sha256":"9332dc33e4034340d32cfa49e74df51614ce9c8446f8cdf23145bb96b4aae9f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:26.274615Z","signature_b64":"pdrHfVbcxYpAa+WEzVqEi6f5LEAc9YVXMic6JuuqzUGBlPXtuUGZoqi8HjAvCkqhEvvOA+x6YTLsZBa3L8GECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd6b1c6888a1f9fa25d7be213672e6b967b8e4b74a32e026eef4797d5f7b0bf0","last_reissued_at":"2026-07-05T09:18:26.274111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:26.274111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MLAE: Masked LoRA Experts for Visual Parameter-Efficient Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangjing Yang, Huahui Yi, Junjie Wang, Qicheng Lao, Wentao Chen, Xiaohu Wu, Zhouchen Lin","submitted_at":"2024-05-29T08:57:23Z","abstract_excerpt":"In response to the challenges posed by the extensive parameter updates required for full fine-tuning of large-scale pre-trained models, parameter-efficient fine-tuning (PEFT) methods, exemplified by Low-Rank Adaptation (LoRA), have emerged. LoRA simplifies the fine-tuning process but may still struggle with a certain level of redundancy in low-rank matrices and limited effectiveness from merely increasing their rank. To address these issues, a natural idea is to enhance the independence and diversity of the learning process for the low-rank matrices. Therefore, we propose Masked LoRA Experts ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18897","kind":"arxiv","version":2},"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/2405.18897/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":"2405.18897","created_at":"2026-07-05T09:18:26.274175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18897v2","created_at":"2026-07-05T09:18:26.274175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18897","created_at":"2026-07-05T09:18:26.274175+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VVRY2EIUH47","created_at":"2026-07-05T09:18:26.274175+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VVRY2EIUH47UJOX","created_at":"2026-07-05T09:18:26.274175+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VVRY2EI","created_at":"2026-07-05T09:18:26.274175+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20745","citing_title":"Regularizing Subspace Redundancy of Low-Rank Adaptation","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3VVRY2EIUH47UJOXXYQTM4XGXF","json":"https://pith.science/pith/3VVRY2EIUH47UJOXXYQTM4XGXF.json","graph_json":"https://pith.science/api/pith-number/3VVRY2EIUH47UJOXXYQTM4XGXF/graph.json","events_json":"https://pith.science/api/pith-number/3VVRY2EIUH47UJOXXYQTM4XGXF/events.json","paper":"https://pith.science/paper/3VVRY2EI"},"agent_actions":{"view_html":"https://pith.science/pith/3VVRY2EIUH47UJOXXYQTM4XGXF","download_json":"https://pith.science/pith/3VVRY2EIUH47UJOXXYQTM4XGXF.json","view_paper":"https://pith.science/paper/3VVRY2EI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18897&json=true","fetch_graph":"https://pith.science/api/pith-number/3VVRY2EIUH47UJOXXYQTM4XGXF/graph.json","fetch_events":"https://pith.science/api/pith-number/3VVRY2EIUH47UJOXXYQTM4XGXF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VVRY2EIUH47UJOXXYQTM4XGXF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VVRY2EIUH47UJOXXYQTM4XGXF/action/storage_attestation","attest_author":"https://pith.science/pith/3VVRY2EIUH47UJOXXYQTM4XGXF/action/author_attestation","sign_citation":"https://pith.science/pith/3VVRY2EIUH47UJOXXYQTM4XGXF/action/citation_signature","submit_replication":"https://pith.science/pith/3VVRY2EIUH47UJOXXYQTM4XGXF/action/replication_record"}},"created_at":"2026-07-05T09:18:26.274175+00:00","updated_at":"2026-07-05T09:18:26.274175+00:00"}