{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VZTCYZZXP7IPTR5PMTVMOIIN4U","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"56c789d3a8cca92f70815069fb726675f792d681a8e88ddebf39c05d56b1290f","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T16:36:38Z","title_canon_sha256":"b0c2b6e28de196bd0e01ed1540fd8dc5855e0be66b9802faea31e35870b7452b"},"schema_version":"1.0","source":{"id":"2410.13733","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13733","created_at":"2026-07-05T09:22:05Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13733v1","created_at":"2026-07-05T09:22:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13733","created_at":"2026-07-05T09:22:05Z"},{"alias_kind":"pith_short_12","alias_value":"VZTCYZZXP7IP","created_at":"2026-07-05T09:22:05Z"},{"alias_kind":"pith_short_16","alias_value":"VZTCYZZXP7IPTR5P","created_at":"2026-07-05T09:22:05Z"},{"alias_kind":"pith_short_8","alias_value":"VZTCYZZX","created_at":"2026-07-05T09:22:05Z"}],"graph_snapshots":[{"event_id":"sha256:58d8d490f24fa928626437082263a3451901ff8ace33ee269b54d50576697d96","target":"graph","created_at":"2026-07-05T09:22:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.13733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gang Zhang, Huaxin Zhang, Jingdong Wang, Nong Sang, Qiang Chen, Xinyu Zhang, Yanpeng Sun, Zechao Li","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T16:36:38Z","title":"Improving Multi-modal Large Language Model through Boosting Vision Capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13733","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cfc2f59a643b01ecfbaab9d9d8f9a39c21955749c363e7e296088a3d1cf7779d","target":"record","created_at":"2026-07-05T09:22:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"56c789d3a8cca92f70815069fb726675f792d681a8e88ddebf39c05d56b1290f","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T16:36:38Z","title_canon_sha256":"b0c2b6e28de196bd0e01ed1540fd8dc5855e0be66b9802faea31e35870b7452b"},"schema_version":"1.0","source":{"id":"2410.13733","kind":"arxiv","version":1}},"canonical_sha256":"ae662c67377fd0f9c7af64eac7210de5231a44f951b8b7c065ecf8a00406a921","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae662c67377fd0f9c7af64eac7210de5231a44f951b8b7c065ecf8a00406a921","first_computed_at":"2026-07-05T09:22:05.054489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:05.054489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SIKrq6ZGRbROXYYYcobxINzvGjYKYzN13riGFpHtJNV6iy1Iy32Eo1qPSxjefOjcsyv6AWJzBn7FlI0zb4awDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:05.054958Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.13733","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfc2f59a643b01ecfbaab9d9d8f9a39c21955749c363e7e296088a3d1cf7779d","sha256:58d8d490f24fa928626437082263a3451901ff8ace33ee269b54d50576697d96"],"state_sha256":"55f14f053db1f78688677f549d91d6e72d3e1895a7a9489bcb3b47c05295539a"}