{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VZTCYZZXP7IPTR5PMTVMOIIN4U","short_pith_number":"pith:VZTCYZZX","schema_version":"1.0","canonical_sha256":"ae662c67377fd0f9c7af64eac7210de5231a44f951b8b7c065ecf8a00406a921","source":{"kind":"arxiv","id":"2410.13733","version":1},"attestation_state":"computed","paper":{"title":"Improving Multi-modal Large Language Model through Boosting Vision Capabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Gang Zhang, Huaxin Zhang, Jingdong Wang, Nong Sang, Qiang Chen, Xinyu Zhang, Yanpeng Sun, Zechao Li","submitted_at":"2024-10-17T16:36:38Z","abstract_excerpt":"We focus on improving the visual understanding capability for boosting the vision-language models. We propose \\textbf{Arcana}, a multiModal language model, which introduces two crucial techniques. First, we present Multimodal LoRA (MM-LoRA), a module designed to enhance the decoder. Unlike traditional language-driven decoders, MM-LoRA consists of two parallel LoRAs -- one for vision and one for language -- each with its own parameters. This disentangled parameters design allows for more specialized learning in each modality and better integration of multimodal information. Second, we introduce"},"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":"2410.13733","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T16:36:38Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"b0c2b6e28de196bd0e01ed1540fd8dc5855e0be66b9802faea31e35870b7452b","abstract_canon_sha256":"56c789d3a8cca92f70815069fb726675f792d681a8e88ddebf39c05d56b1290f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:05.054958Z","signature_b64":"SIKrq6ZGRbROXYYYcobxINzvGjYKYzN13riGFpHtJNV6iy1Iy32Eo1qPSxjefOjcsyv6AWJzBn7FlI0zb4awDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae662c67377fd0f9c7af64eac7210de5231a44f951b8b7c065ecf8a00406a921","last_reissued_at":"2026-07-05T09:22:05.054489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:05.054489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Multi-modal Large Language Model through Boosting Vision Capabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Gang Zhang, Huaxin Zhang, Jingdong Wang, Nong Sang, Qiang Chen, Xinyu Zhang, Yanpeng Sun, Zechao Li","submitted_at":"2024-10-17T16:36:38Z","abstract_excerpt":"We focus on improving the visual understanding capability for boosting the vision-language models. We propose \\textbf{Arcana}, a multiModal language model, which introduces two crucial techniques. First, we present Multimodal LoRA (MM-LoRA), a module designed to enhance the decoder. Unlike traditional language-driven decoders, MM-LoRA consists of two parallel LoRAs -- one for vision and one for language -- each with its own parameters. This disentangled parameters design allows for more specialized learning in each modality and better integration of multimodal information. Second, we introduce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13733","kind":"arxiv","version":1},"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/2410.13733/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":"2410.13733","created_at":"2026-07-05T09:22:05.054548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13733v1","created_at":"2026-07-05T09:22:05.054548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13733","created_at":"2026-07-05T09:22:05.054548+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZTCYZZXP7IP","created_at":"2026-07-05T09:22:05.054548+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZTCYZZXP7IPTR5P","created_at":"2026-07-05T09:22:05.054548+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZTCYZZX","created_at":"2026-07-05T09:22:05.054548+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14797","citing_title":"Continual SFT Matches Multimodal RLHF with Negative Supervision","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZTCYZZXP7IPTR5PMTVMOIIN4U","json":"https://pith.science/pith/VZTCYZZXP7IPTR5PMTVMOIIN4U.json","graph_json":"https://pith.science/api/pith-number/VZTCYZZXP7IPTR5PMTVMOIIN4U/graph.json","events_json":"https://pith.science/api/pith-number/VZTCYZZXP7IPTR5PMTVMOIIN4U/events.json","paper":"https://pith.science/paper/VZTCYZZX"},"agent_actions":{"view_html":"https://pith.science/pith/VZTCYZZXP7IPTR5PMTVMOIIN4U","download_json":"https://pith.science/pith/VZTCYZZXP7IPTR5PMTVMOIIN4U.json","view_paper":"https://pith.science/paper/VZTCYZZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13733&json=true","fetch_graph":"https://pith.science/api/pith-number/VZTCYZZXP7IPTR5PMTVMOIIN4U/graph.json","fetch_events":"https://pith.science/api/pith-number/VZTCYZZXP7IPTR5PMTVMOIIN4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZTCYZZXP7IPTR5PMTVMOIIN4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZTCYZZXP7IPTR5PMTVMOIIN4U/action/storage_attestation","attest_author":"https://pith.science/pith/VZTCYZZXP7IPTR5PMTVMOIIN4U/action/author_attestation","sign_citation":"https://pith.science/pith/VZTCYZZXP7IPTR5PMTVMOIIN4U/action/citation_signature","submit_replication":"https://pith.science/pith/VZTCYZZXP7IPTR5PMTVMOIIN4U/action/replication_record"}},"created_at":"2026-07-05T09:22:05.054548+00:00","updated_at":"2026-07-05T09:22:05.054548+00:00"}