{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GBCVWHUXMQAQQCXGHEE2WLQG3O","short_pith_number":"pith:GBCVWHUX","schema_version":"1.0","canonical_sha256":"30455b1e976401080ae63909ab2e06dbb766ade082219de9b1a78f5f05a8f4fe","source":{"kind":"arxiv","id":"2406.17770","version":2},"attestation_state":"computed","paper":{"title":"MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haian Huang, Haodong Duan, Hua Yang, Kai Chen, Xiangtai Li, Xiangyu Zhao, Yining Li","submitted_at":"2024-06-25T17:55:11Z","abstract_excerpt":"Multi-modal large language models (MLLMs) have made significant strides in various visual understanding tasks. However, the majority of these models are constrained to process low-resolution images, which limits their effectiveness in perception tasks that necessitate detailed visual information. In our study, we present MG-LLaVA, an innovative MLLM that enhances the model's visual processing capabilities by incorporating a multi-granularity vision flow, which includes low-resolution, high-resolution, and object-centric features. We propose the integration of an additional high-resolution visu"},"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":"2406.17770","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-25T17:55:11Z","cross_cats_sorted":[],"title_canon_sha256":"b260c63c914c3b710bbbe9c0bf046455b919f0dea1feb66ac1196d76c402f254","abstract_canon_sha256":"ebd563ae03523808367e704334aef967ea41a6891e4bd050ff5fe0412a24a959"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:21.356779Z","signature_b64":"Mx5n0GQqsjxx+FGqVYMPq86IBPq0+rPp1QCUdEiyRxNnvbV3bRDg7RK6UBlyloB5aYjB04BIlyKjLGgZXqtPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30455b1e976401080ae63909ab2e06dbb766ade082219de9b1a78f5f05a8f4fe","last_reissued_at":"2026-07-05T08:37:21.356304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:21.356304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haian Huang, Haodong Duan, Hua Yang, Kai Chen, Xiangtai Li, Xiangyu Zhao, Yining Li","submitted_at":"2024-06-25T17:55:11Z","abstract_excerpt":"Multi-modal large language models (MLLMs) have made significant strides in various visual understanding tasks. However, the majority of these models are constrained to process low-resolution images, which limits their effectiveness in perception tasks that necessitate detailed visual information. In our study, we present MG-LLaVA, an innovative MLLM that enhances the model's visual processing capabilities by incorporating a multi-granularity vision flow, which includes low-resolution, high-resolution, and object-centric features. We propose the integration of an additional high-resolution visu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17770","kind":"arxiv","version":2},"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/2406.17770/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":"2406.17770","created_at":"2026-07-05T08:37:21.356367+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.17770v2","created_at":"2026-07-05T08:37:21.356367+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17770","created_at":"2026-07-05T08:37:21.356367+00:00"},{"alias_kind":"pith_short_12","alias_value":"GBCVWHUXMQAQ","created_at":"2026-07-05T08:37:21.356367+00:00"},{"alias_kind":"pith_short_16","alias_value":"GBCVWHUXMQAQQCXG","created_at":"2026-07-05T08:37:21.356367+00:00"},{"alias_kind":"pith_short_8","alias_value":"GBCVWHUX","created_at":"2026-07-05T08:37:21.356367+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14928","citing_title":"Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QA","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18018","citing_title":"See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding","ref_index":111,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GBCVWHUXMQAQQCXGHEE2WLQG3O","json":"https://pith.science/pith/GBCVWHUXMQAQQCXGHEE2WLQG3O.json","graph_json":"https://pith.science/api/pith-number/GBCVWHUXMQAQQCXGHEE2WLQG3O/graph.json","events_json":"https://pith.science/api/pith-number/GBCVWHUXMQAQQCXGHEE2WLQG3O/events.json","paper":"https://pith.science/paper/GBCVWHUX"},"agent_actions":{"view_html":"https://pith.science/pith/GBCVWHUXMQAQQCXGHEE2WLQG3O","download_json":"https://pith.science/pith/GBCVWHUXMQAQQCXGHEE2WLQG3O.json","view_paper":"https://pith.science/paper/GBCVWHUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.17770&json=true","fetch_graph":"https://pith.science/api/pith-number/GBCVWHUXMQAQQCXGHEE2WLQG3O/graph.json","fetch_events":"https://pith.science/api/pith-number/GBCVWHUXMQAQQCXGHEE2WLQG3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GBCVWHUXMQAQQCXGHEE2WLQG3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GBCVWHUXMQAQQCXGHEE2WLQG3O/action/storage_attestation","attest_author":"https://pith.science/pith/GBCVWHUXMQAQQCXGHEE2WLQG3O/action/author_attestation","sign_citation":"https://pith.science/pith/GBCVWHUXMQAQQCXGHEE2WLQG3O/action/citation_signature","submit_replication":"https://pith.science/pith/GBCVWHUXMQAQQCXGHEE2WLQG3O/action/replication_record"}},"created_at":"2026-07-05T08:37:21.356367+00:00","updated_at":"2026-07-05T08:37:21.356367+00:00"}