{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PYHNDJ2ISBGS26ABGGTFKSGHKT","short_pith_number":"pith:PYHNDJ2I","schema_version":"1.0","canonical_sha256":"7e0ed1a748904d2d780131a65548c754e174146712f899e8ea34b27ad130407b","source":{"kind":"arxiv","id":"2409.15657","version":4},"attestation_state":"computed","paper":{"title":"M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Cheng Han, Dongfang Liu, Fuli Feng, James Chenhao Liang, Jiahao Liu, Junhan Zhao, Lifu Huang, Qifan Wang, Shaoliang Nie, Taowen Wang, Yiming Cui, Yiyang Liu, Yuning Mao, Zenglin Xu","submitted_at":"2024-09-24T01:40:24Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) demonstrate remarkable performance across a wide range of domains, with increasing emphasis on enhancing their zero-shot generalization capabilities for unseen tasks across various modalities. Instruction tuning has emerged as an effective strategy for achieving zero-shot generalization by finetuning pretrained models on diverse multimodal tasks. As the scale of MLLMs continues to grow, parameter-efficient finetuning becomes increasingly critical. However, most existing parameter-efficient approaches focus only on single modalities and often overlook th"},"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":"2409.15657","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-09-24T01:40:24Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"dccab5b6880b7e7dd71f10278e0bd2ecfb1629d884f2574ccf1dc304aa2ec845","abstract_canon_sha256":"350e410ff467c07b9c0e85cf2d3f21ff6e388ca3e2ecf54b6124d6689599dd71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:13.793773Z","signature_b64":"78iZAgHVh5oHLoKP723gTje5IwdHsCFy56azYrmW+UhsoRYYWma/ZvEeWCh/9xEUAQUflxWVBpu0quQCXTfjCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e0ed1a748904d2d780131a65548c754e174146712f899e8ea34b27ad130407b","last_reissued_at":"2026-07-05T09:28:13.793312Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:13.793312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Cheng Han, Dongfang Liu, Fuli Feng, James Chenhao Liang, Jiahao Liu, Junhan Zhao, Lifu Huang, Qifan Wang, Shaoliang Nie, Taowen Wang, Yiming Cui, Yiyang Liu, Yuning Mao, Zenglin Xu","submitted_at":"2024-09-24T01:40:24Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) demonstrate remarkable performance across a wide range of domains, with increasing emphasis on enhancing their zero-shot generalization capabilities for unseen tasks across various modalities. Instruction tuning has emerged as an effective strategy for achieving zero-shot generalization by finetuning pretrained models on diverse multimodal tasks. As the scale of MLLMs continues to grow, parameter-efficient finetuning becomes increasingly critical. However, most existing parameter-efficient approaches focus only on single modalities and often overlook th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15657","kind":"arxiv","version":4},"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/2409.15657/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":"2409.15657","created_at":"2026-07-05T09:28:13.793378+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.15657v4","created_at":"2026-07-05T09:28:13.793378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15657","created_at":"2026-07-05T09:28:13.793378+00:00"},{"alias_kind":"pith_short_12","alias_value":"PYHNDJ2ISBGS","created_at":"2026-07-05T09:28:13.793378+00:00"},{"alias_kind":"pith_short_16","alias_value":"PYHNDJ2ISBGS26AB","created_at":"2026-07-05T09:28:13.793378+00:00"},{"alias_kind":"pith_short_8","alias_value":"PYHNDJ2I","created_at":"2026-07-05T09:28:13.793378+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/PYHNDJ2ISBGS26ABGGTFKSGHKT","json":"https://pith.science/pith/PYHNDJ2ISBGS26ABGGTFKSGHKT.json","graph_json":"https://pith.science/api/pith-number/PYHNDJ2ISBGS26ABGGTFKSGHKT/graph.json","events_json":"https://pith.science/api/pith-number/PYHNDJ2ISBGS26ABGGTFKSGHKT/events.json","paper":"https://pith.science/paper/PYHNDJ2I"},"agent_actions":{"view_html":"https://pith.science/pith/PYHNDJ2ISBGS26ABGGTFKSGHKT","download_json":"https://pith.science/pith/PYHNDJ2ISBGS26ABGGTFKSGHKT.json","view_paper":"https://pith.science/paper/PYHNDJ2I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.15657&json=true","fetch_graph":"https://pith.science/api/pith-number/PYHNDJ2ISBGS26ABGGTFKSGHKT/graph.json","fetch_events":"https://pith.science/api/pith-number/PYHNDJ2ISBGS26ABGGTFKSGHKT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PYHNDJ2ISBGS26ABGGTFKSGHKT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PYHNDJ2ISBGS26ABGGTFKSGHKT/action/storage_attestation","attest_author":"https://pith.science/pith/PYHNDJ2ISBGS26ABGGTFKSGHKT/action/author_attestation","sign_citation":"https://pith.science/pith/PYHNDJ2ISBGS26ABGGTFKSGHKT/action/citation_signature","submit_replication":"https://pith.science/pith/PYHNDJ2ISBGS26ABGGTFKSGHKT/action/replication_record"}},"created_at":"2026-07-05T09:28:13.793378+00:00","updated_at":"2026-07-05T09:28:13.793378+00:00"}