{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HPS7QFEY2CUXWUP2IQ2QXBPUP3","short_pith_number":"pith:HPS7QFEY","schema_version":"1.0","canonical_sha256":"3be5f81498d0a97b51fa44350b85f47ef3c3971be372ec0ac7cc2f290bd33a83","source":{"kind":"arxiv","id":"2506.01663","version":2},"attestation_state":"computed","paper":{"title":"Zoom-Refine: Boosting High-Resolution Multimodal Understanding via Localized Zoom and Self-Refinement","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dayan Guan, Xuan Yu, Yanfeng Gu","submitted_at":"2025-06-02T13:32:35Z","abstract_excerpt":"Multimodal Large Language Models (MLLM) often struggle to interpret high-resolution images accurately, where fine-grained details are crucial for complex visual understanding. We introduce Zoom-Refine, a novel training-free method that enhances MLLM capabilities to address this issue. Zoom-Refine operates through a synergistic process of \\textit{Localized Zoom} and \\textit{Self-Refinement}. In the \\textit{Localized Zoom} step, Zoom-Refine leverages the MLLM to provide a preliminary response to an input query and identifies the most task-relevant image region by predicting its bounding box coor"},"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":"2506.01663","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T13:32:35Z","cross_cats_sorted":[],"title_canon_sha256":"51a31485d90e2297ae94720bb2ca66ac000dab6ea70234814981af721f8198bf","abstract_canon_sha256":"c814a075428bd1e658d13bf3ddac661a1b54c08bc256338c8112efcf3ab40b30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:27.976131Z","signature_b64":"JE3Biks67cKCiZ7Hpr46zYa3SXEjQJxCrkL8MQBWQZf99GU/Z2pd+7DPbFJiGbb98PU2gSxlikZB7LxY5Cd0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3be5f81498d0a97b51fa44350b85f47ef3c3971be372ec0ac7cc2f290bd33a83","last_reissued_at":"2026-07-05T11:51:27.975645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:27.975645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zoom-Refine: Boosting High-Resolution Multimodal Understanding via Localized Zoom and Self-Refinement","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dayan Guan, Xuan Yu, Yanfeng Gu","submitted_at":"2025-06-02T13:32:35Z","abstract_excerpt":"Multimodal Large Language Models (MLLM) often struggle to interpret high-resolution images accurately, where fine-grained details are crucial for complex visual understanding. We introduce Zoom-Refine, a novel training-free method that enhances MLLM capabilities to address this issue. Zoom-Refine operates through a synergistic process of \\textit{Localized Zoom} and \\textit{Self-Refinement}. In the \\textit{Localized Zoom} step, Zoom-Refine leverages the MLLM to provide a preliminary response to an input query and identifies the most task-relevant image region by predicting its bounding box coor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01663","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/2506.01663/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":"2506.01663","created_at":"2026-07-05T11:51:27.975718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01663v2","created_at":"2026-07-05T11:51:27.975718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01663","created_at":"2026-07-05T11:51:27.975718+00:00"},{"alias_kind":"pith_short_12","alias_value":"HPS7QFEY2CUX","created_at":"2026-07-05T11:51:27.975718+00:00"},{"alias_kind":"pith_short_16","alias_value":"HPS7QFEY2CUXWUP2","created_at":"2026-07-05T11:51:27.975718+00:00"},{"alias_kind":"pith_short_8","alias_value":"HPS7QFEY","created_at":"2026-07-05T11:51:27.975718+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"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":138,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01191","citing_title":"Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18740","citing_title":"Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30288","citing_title":"VisReflect: Latent Visual Reflection for Fine-Grained Perception in Long Visual Context","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27960","citing_title":"Mags-RL: Wearing Multimodal LLMs a Magnifying Glass via Agentic Reinforcement Learning For Complex Scene Reasoning","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00562","citing_title":"DeepLatent: Think with Images via Parallel Latent Visual Reasoning","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18740","citing_title":"Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02730","citing_title":"Perceptual Flow Network for Visually Grounded Reasoning","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HPS7QFEY2CUXWUP2IQ2QXBPUP3","json":"https://pith.science/pith/HPS7QFEY2CUXWUP2IQ2QXBPUP3.json","graph_json":"https://pith.science/api/pith-number/HPS7QFEY2CUXWUP2IQ2QXBPUP3/graph.json","events_json":"https://pith.science/api/pith-number/HPS7QFEY2CUXWUP2IQ2QXBPUP3/events.json","paper":"https://pith.science/paper/HPS7QFEY"},"agent_actions":{"view_html":"https://pith.science/pith/HPS7QFEY2CUXWUP2IQ2QXBPUP3","download_json":"https://pith.science/pith/HPS7QFEY2CUXWUP2IQ2QXBPUP3.json","view_paper":"https://pith.science/paper/HPS7QFEY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01663&json=true","fetch_graph":"https://pith.science/api/pith-number/HPS7QFEY2CUXWUP2IQ2QXBPUP3/graph.json","fetch_events":"https://pith.science/api/pith-number/HPS7QFEY2CUXWUP2IQ2QXBPUP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HPS7QFEY2CUXWUP2IQ2QXBPUP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HPS7QFEY2CUXWUP2IQ2QXBPUP3/action/storage_attestation","attest_author":"https://pith.science/pith/HPS7QFEY2CUXWUP2IQ2QXBPUP3/action/author_attestation","sign_citation":"https://pith.science/pith/HPS7QFEY2CUXWUP2IQ2QXBPUP3/action/citation_signature","submit_replication":"https://pith.science/pith/HPS7QFEY2CUXWUP2IQ2QXBPUP3/action/replication_record"}},"created_at":"2026-07-05T11:51:27.975718+00:00","updated_at":"2026-07-05T11:51:27.975718+00:00"}