{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CDYOOFFC5VSLLZG7NI2KRWDXXM","short_pith_number":"pith:CDYOOFFC","schema_version":"1.0","canonical_sha256":"10f0e714a2ed64b5e4df6a34a8d877bb0f385c916b830a232cf9589847f7cfda","source":{"kind":"arxiv","id":"2504.14920","version":1},"attestation_state":"computed","paper":{"title":"DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Geng Li, Jinglin Xu, Yunzhen Zhao, Yuxin Peng","submitted_at":"2025-04-21T07:39:29Z","abstract_excerpt":"Humans can effortlessly locate desired objects in cluttered environments, relying on a cognitive mechanism known as visual search to efficiently filter out irrelevant information and focus on task-related regions. Inspired by this process, we propose Dyfo (Dynamic Focus), a training-free dynamic focusing visual search method that enhances fine-grained visual understanding in large multimodal models (LMMs). Unlike existing approaches which require additional modules or data collection, Dyfo leverages a bidirectional interaction between LMMs and visual experts, using a Monte Carlo Tree Search (M"},"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":"2504.14920","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T07:39:29Z","cross_cats_sorted":[],"title_canon_sha256":"420c47eb50775fa9505e9b721caaaf7999aed8e4172e2467c19a7f6af1d99402","abstract_canon_sha256":"8cd0c57758bbb44884d893e3a6f15f5ad552e9be1e7b4cb905d6fff9034a3cf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:53.346123Z","signature_b64":"gxYuwz5OEB0bKunHSwgOpZKFRmov1M8Y8Do+cNhhWFSt+LfL/RX+oRzphhOTRfkJxC+4laV2qO60edU61HOiBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10f0e714a2ed64b5e4df6a34a8d877bb0f385c916b830a232cf9589847f7cfda","last_reissued_at":"2026-07-05T10:51:53.345632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:53.345632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Geng Li, Jinglin Xu, Yunzhen Zhao, Yuxin Peng","submitted_at":"2025-04-21T07:39:29Z","abstract_excerpt":"Humans can effortlessly locate desired objects in cluttered environments, relying on a cognitive mechanism known as visual search to efficiently filter out irrelevant information and focus on task-related regions. Inspired by this process, we propose Dyfo (Dynamic Focus), a training-free dynamic focusing visual search method that enhances fine-grained visual understanding in large multimodal models (LMMs). Unlike existing approaches which require additional modules or data collection, Dyfo leverages a bidirectional interaction between LMMs and visual experts, using a Monte Carlo Tree Search (M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14920","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/2504.14920/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":"2504.14920","created_at":"2026-07-05T10:51:53.345695+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14920v1","created_at":"2026-07-05T10:51:53.345695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14920","created_at":"2026-07-05T10:51:53.345695+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDYOOFFC5VSL","created_at":"2026-07-05T10:51:53.345695+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDYOOFFC5VSLLZG7","created_at":"2026-07-05T10:51:53.345695+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDYOOFFC","created_at":"2026-07-05T10:51:53.345695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25319","citing_title":"V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28741","citing_title":"Self-Prophetic Decoding to Unlock Visual Search in LVLMs","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2509.07969","citing_title":"Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09167","citing_title":"MAG-3D: Multi-Agent Grounded Reasoning for 3D Understanding","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CDYOOFFC5VSLLZG7NI2KRWDXXM","json":"https://pith.science/pith/CDYOOFFC5VSLLZG7NI2KRWDXXM.json","graph_json":"https://pith.science/api/pith-number/CDYOOFFC5VSLLZG7NI2KRWDXXM/graph.json","events_json":"https://pith.science/api/pith-number/CDYOOFFC5VSLLZG7NI2KRWDXXM/events.json","paper":"https://pith.science/paper/CDYOOFFC"},"agent_actions":{"view_html":"https://pith.science/pith/CDYOOFFC5VSLLZG7NI2KRWDXXM","download_json":"https://pith.science/pith/CDYOOFFC5VSLLZG7NI2KRWDXXM.json","view_paper":"https://pith.science/paper/CDYOOFFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14920&json=true","fetch_graph":"https://pith.science/api/pith-number/CDYOOFFC5VSLLZG7NI2KRWDXXM/graph.json","fetch_events":"https://pith.science/api/pith-number/CDYOOFFC5VSLLZG7NI2KRWDXXM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDYOOFFC5VSLLZG7NI2KRWDXXM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDYOOFFC5VSLLZG7NI2KRWDXXM/action/storage_attestation","attest_author":"https://pith.science/pith/CDYOOFFC5VSLLZG7NI2KRWDXXM/action/author_attestation","sign_citation":"https://pith.science/pith/CDYOOFFC5VSLLZG7NI2KRWDXXM/action/citation_signature","submit_replication":"https://pith.science/pith/CDYOOFFC5VSLLZG7NI2KRWDXXM/action/replication_record"}},"created_at":"2026-07-05T10:51:53.345695+00:00","updated_at":"2026-07-05T10:51:53.345695+00:00"}