{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KPTCNBD2TE34YA7JPVICIJCTE5","short_pith_number":"pith:KPTCNBD2","schema_version":"1.0","canonical_sha256":"53e626847a9937cc03e97d5024245327565311e5e4029513d3b43cb714e514cc","source":{"kind":"arxiv","id":"2402.14767","version":1},"attestation_state":"computed","paper":{"title":"DualFocus: Integrating Macro and Micro Perspectives in Multi-modal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Jiaqi Wang, Pan Zhang, Xiaoyi Dong, Yuhang Cao","submitted_at":"2024-02-22T18:26:02Z","abstract_excerpt":"We present DualFocus, a novel framework for integrating macro and micro perspectives within multi-modal large language models (MLLMs) to enhance vision-language task performance. Current MLLMs typically singularly focus on inputs at a predefined resolution, resulting in deficiencies in detailed questions involving local regions. We introduced a DualFocus mechanism where the model concentrates on the image from a macro perspective, responses to the question, and identifies suitable sub-regions to zoom in for subsequent micro perspective analysis. Via the integration of answers from both macro a"},"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":"2402.14767","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-22T18:26:02Z","cross_cats_sorted":[],"title_canon_sha256":"b4a25bd0df4086b2c91bc9ee5b86208136fe4d9ca65cbc3a981bff610e488182","abstract_canon_sha256":"25d61a87d31e8f22a0f07020a22093d1b7235dd139277f197c8bd140f75022d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:14.292775Z","signature_b64":"8+DXDSeTd3O3+WSl8VzMSB3bI8iaW4NWxC983KAQtJ7j0iqxeiwRidpj3Eom3cS9+2nsE2Aphg8livJm8swZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53e626847a9937cc03e97d5024245327565311e5e4029513d3b43cb714e514cc","last_reissued_at":"2026-07-05T07:48:14.292266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:14.292266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DualFocus: Integrating Macro and Micro Perspectives in Multi-modal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Jiaqi Wang, Pan Zhang, Xiaoyi Dong, Yuhang Cao","submitted_at":"2024-02-22T18:26:02Z","abstract_excerpt":"We present DualFocus, a novel framework for integrating macro and micro perspectives within multi-modal large language models (MLLMs) to enhance vision-language task performance. Current MLLMs typically singularly focus on inputs at a predefined resolution, resulting in deficiencies in detailed questions involving local regions. We introduced a DualFocus mechanism where the model concentrates on the image from a macro perspective, responses to the question, and identifies suitable sub-regions to zoom in for subsequent micro perspective analysis. Via the integration of answers from both macro a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14767","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/2402.14767/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":"2402.14767","created_at":"2026-07-05T07:48:14.292326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14767v1","created_at":"2026-07-05T07:48:14.292326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14767","created_at":"2026-07-05T07:48:14.292326+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPTCNBD2TE34","created_at":"2026-07-05T07:48:14.292326+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPTCNBD2TE34YA7J","created_at":"2026-07-05T07:48:14.292326+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPTCNBD2","created_at":"2026-07-05T07:48:14.292326+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":129,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26994","citing_title":"Event-Aware Instructed Assistant for Referring Video Segmentation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2407.03320","citing_title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KPTCNBD2TE34YA7JPVICIJCTE5","json":"https://pith.science/pith/KPTCNBD2TE34YA7JPVICIJCTE5.json","graph_json":"https://pith.science/api/pith-number/KPTCNBD2TE34YA7JPVICIJCTE5/graph.json","events_json":"https://pith.science/api/pith-number/KPTCNBD2TE34YA7JPVICIJCTE5/events.json","paper":"https://pith.science/paper/KPTCNBD2"},"agent_actions":{"view_html":"https://pith.science/pith/KPTCNBD2TE34YA7JPVICIJCTE5","download_json":"https://pith.science/pith/KPTCNBD2TE34YA7JPVICIJCTE5.json","view_paper":"https://pith.science/paper/KPTCNBD2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14767&json=true","fetch_graph":"https://pith.science/api/pith-number/KPTCNBD2TE34YA7JPVICIJCTE5/graph.json","fetch_events":"https://pith.science/api/pith-number/KPTCNBD2TE34YA7JPVICIJCTE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPTCNBD2TE34YA7JPVICIJCTE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPTCNBD2TE34YA7JPVICIJCTE5/action/storage_attestation","attest_author":"https://pith.science/pith/KPTCNBD2TE34YA7JPVICIJCTE5/action/author_attestation","sign_citation":"https://pith.science/pith/KPTCNBD2TE34YA7JPVICIJCTE5/action/citation_signature","submit_replication":"https://pith.science/pith/KPTCNBD2TE34YA7JPVICIJCTE5/action/replication_record"}},"created_at":"2026-07-05T07:48:14.292326+00:00","updated_at":"2026-07-05T07:48:14.292326+00:00"}