{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B2PU2M2ZNNHXIFXQ6X6ZP5JKNI","short_pith_number":"pith:B2PU2M2Z","schema_version":"1.0","canonical_sha256":"0e9f4d33596b4f7416f0f5fd97f52a6a121160df9c85824da625580f30fefab7","source":{"kind":"arxiv","id":"2403.05060","version":3},"attestation_state":"computed","paper":{"title":"Multimodal Infusion Tuning for Large Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.MM","authors_text":"Hao Sun, Jiaqing Liu, Lanfen Lin, Xinyao Yu, Yen-Wei Chen, Yu Song","submitted_at":"2024-03-08T05:15:05Z","abstract_excerpt":"Recent advancements in large-scale models have showcased remarkable generalization capabilities in various tasks. However, integrating multimodal processing into these models presents a significant challenge, as it often comes with a high computational burden. To address this challenge, we introduce a new parameter-efficient multimodal tuning strategy for large models in this paper, referred to as Multimodal Infusion Tuning (MiT). MiT leverages decoupled self-attention mechanisms within large language models to effectively integrate information from diverse modalities such as images and acoust"},"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":"2403.05060","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-03-08T05:15:05Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"89fc5ae69b3f6744733bebcffa3c9f06e7bedb22356add265b29b99c616f42eb","abstract_canon_sha256":"a46dc5d8d8e5a2fb6a6a5f3c1ee1f97cb52ca8b52b1859eb2f43600fe35360ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:12.517826Z","signature_b64":"j0W3VNOSp0ecvnPB2a+YqVG6fwJm9OZnsrQXb75teQemBnnHdhT/Q2N6NE7852Iovfk92b2Mk8VmTYouT6sGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e9f4d33596b4f7416f0f5fd97f52a6a121160df9c85824da625580f30fefab7","last_reissued_at":"2026-07-05T08:44:12.517285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:12.517285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Infusion Tuning for Large Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.MM","authors_text":"Hao Sun, Jiaqing Liu, Lanfen Lin, Xinyao Yu, Yen-Wei Chen, Yu Song","submitted_at":"2024-03-08T05:15:05Z","abstract_excerpt":"Recent advancements in large-scale models have showcased remarkable generalization capabilities in various tasks. However, integrating multimodal processing into these models presents a significant challenge, as it often comes with a high computational burden. To address this challenge, we introduce a new parameter-efficient multimodal tuning strategy for large models in this paper, referred to as Multimodal Infusion Tuning (MiT). MiT leverages decoupled self-attention mechanisms within large language models to effectively integrate information from diverse modalities such as images and acoust"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05060","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/2403.05060/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":"2403.05060","created_at":"2026-07-05T08:44:12.517345+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.05060v3","created_at":"2026-07-05T08:44:12.517345+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05060","created_at":"2026-07-05T08:44:12.517345+00:00"},{"alias_kind":"pith_short_12","alias_value":"B2PU2M2ZNNHX","created_at":"2026-07-05T08:44:12.517345+00:00"},{"alias_kind":"pith_short_16","alias_value":"B2PU2M2ZNNHXIFXQ","created_at":"2026-07-05T08:44:12.517345+00:00"},{"alias_kind":"pith_short_8","alias_value":"B2PU2M2Z","created_at":"2026-07-05T08:44:12.517345+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/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI","json":"https://pith.science/pith/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI.json","graph_json":"https://pith.science/api/pith-number/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI/graph.json","events_json":"https://pith.science/api/pith-number/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI/events.json","paper":"https://pith.science/paper/B2PU2M2Z"},"agent_actions":{"view_html":"https://pith.science/pith/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI","download_json":"https://pith.science/pith/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI.json","view_paper":"https://pith.science/paper/B2PU2M2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.05060&json=true","fetch_graph":"https://pith.science/api/pith-number/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI/graph.json","fetch_events":"https://pith.science/api/pith-number/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI/action/storage_attestation","attest_author":"https://pith.science/pith/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI/action/author_attestation","sign_citation":"https://pith.science/pith/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI/action/citation_signature","submit_replication":"https://pith.science/pith/B2PU2M2ZNNHXIFXQ6X6ZP5JKNI/action/replication_record"}},"created_at":"2026-07-05T08:44:12.517345+00:00","updated_at":"2026-07-05T08:44:12.517345+00:00"}