{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4QVIVSA67ZZJ3XBEXZRYL43KRP","short_pith_number":"pith:4QVIVSA6","schema_version":"1.0","canonical_sha256":"e42a8ac81efe729ddc24be6385f36a8bdd3917fac2c3a1f159ec0392c660fac6","source":{"kind":"arxiv","id":"2410.09437","version":3},"attestation_state":"computed","paper":{"title":"MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Denvy Deng, Dilxat Muhtar, Feng Sun, Hao Sun, Jianfeng Liu, Qi Zhang, Weizhu Chen, Yaming Yang, Yelong Shen, Yuefeng Zhan, Yujing Wang, Yunhai Tong","submitted_at":"2024-10-12T08:32:26Z","abstract_excerpt":"Parameter-efficient fine-tuning (PEFT) has been widely employed for domain adaptation, with LoRA being one of the most prominent methods due to its simplicity and effectiveness. However, in multi-task learning (MTL) scenarios, LoRA tends to obscure the distinction between tasks by projecting sparse high-dimensional features from different tasks into the same dense low-dimensional intrinsic space. This leads to task interference and suboptimal performance for LoRA and its variants. To tackle this challenge, we propose MTL-LoRA, which retains the advantages of low-rank adaptation while significa"},"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":"2410.09437","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-12T08:32:26Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"2d9841cc2b394b57fa7ab470c589ec4aa12c4f17a36988bf9132efdc484ac2c1","abstract_canon_sha256":"f0a19e69bc575e787280de7ea8e23dc970bdc2568abd29e2f422e048e9448e23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:37.981789Z","signature_b64":"8/ydd8RLmXSgehaEwmj0trnyDniP9/2eJREbvUlvdo5tGjNqerfYezq49H7Nm/UIEEmEP4YF+MiIueLCmZGSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e42a8ac81efe729ddc24be6385f36a8bdd3917fac2c3a1f159ec0392c660fac6","last_reissued_at":"2026-07-05T10:42:37.981284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:37.981284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Denvy Deng, Dilxat Muhtar, Feng Sun, Hao Sun, Jianfeng Liu, Qi Zhang, Weizhu Chen, Yaming Yang, Yelong Shen, Yuefeng Zhan, Yujing Wang, Yunhai Tong","submitted_at":"2024-10-12T08:32:26Z","abstract_excerpt":"Parameter-efficient fine-tuning (PEFT) has been widely employed for domain adaptation, with LoRA being one of the most prominent methods due to its simplicity and effectiveness. However, in multi-task learning (MTL) scenarios, LoRA tends to obscure the distinction between tasks by projecting sparse high-dimensional features from different tasks into the same dense low-dimensional intrinsic space. This leads to task interference and suboptimal performance for LoRA and its variants. To tackle this challenge, we propose MTL-LoRA, which retains the advantages of low-rank adaptation while significa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09437","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/2410.09437/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":"2410.09437","created_at":"2026-07-05T10:42:37.981350+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09437v3","created_at":"2026-07-05T10:42:37.981350+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09437","created_at":"2026-07-05T10:42:37.981350+00:00"},{"alias_kind":"pith_short_12","alias_value":"4QVIVSA67ZZJ","created_at":"2026-07-05T10:42:37.981350+00:00"},{"alias_kind":"pith_short_16","alias_value":"4QVIVSA67ZZJ3XBE","created_at":"2026-07-05T10:42:37.981350+00:00"},{"alias_kind":"pith_short_8","alias_value":"4QVIVSA6","created_at":"2026-07-05T10:42:37.981350+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/4QVIVSA67ZZJ3XBEXZRYL43KRP","json":"https://pith.science/pith/4QVIVSA67ZZJ3XBEXZRYL43KRP.json","graph_json":"https://pith.science/api/pith-number/4QVIVSA67ZZJ3XBEXZRYL43KRP/graph.json","events_json":"https://pith.science/api/pith-number/4QVIVSA67ZZJ3XBEXZRYL43KRP/events.json","paper":"https://pith.science/paper/4QVIVSA6"},"agent_actions":{"view_html":"https://pith.science/pith/4QVIVSA67ZZJ3XBEXZRYL43KRP","download_json":"https://pith.science/pith/4QVIVSA67ZZJ3XBEXZRYL43KRP.json","view_paper":"https://pith.science/paper/4QVIVSA6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09437&json=true","fetch_graph":"https://pith.science/api/pith-number/4QVIVSA67ZZJ3XBEXZRYL43KRP/graph.json","fetch_events":"https://pith.science/api/pith-number/4QVIVSA67ZZJ3XBEXZRYL43KRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4QVIVSA67ZZJ3XBEXZRYL43KRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4QVIVSA67ZZJ3XBEXZRYL43KRP/action/storage_attestation","attest_author":"https://pith.science/pith/4QVIVSA67ZZJ3XBEXZRYL43KRP/action/author_attestation","sign_citation":"https://pith.science/pith/4QVIVSA67ZZJ3XBEXZRYL43KRP/action/citation_signature","submit_replication":"https://pith.science/pith/4QVIVSA67ZZJ3XBEXZRYL43KRP/action/replication_record"}},"created_at":"2026-07-05T10:42:37.981350+00:00","updated_at":"2026-07-05T10:42:37.981350+00:00"}