{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O3P5L7RMKN7KBGL5XSVSHTZFI4","short_pith_number":"pith:O3P5L7RM","schema_version":"1.0","canonical_sha256":"76dfd5fe2c537ea0997dbcab23cf25472e6d30d17c0cdb6a5b2931160d8918ba","source":{"kind":"arxiv","id":"2501.05767","version":3},"attestation_state":"computed","paper":{"title":"Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Chao Huang, Chi Chen, Heyu Huang, Jinan Xu, Kaiyu Huang, Maosong Sun, Ruixuan Li, You Li, Yuhua Li, Zhiyuan Liu, Zonghao Guo","submitted_at":"2025-01-10T07:56:23Z","abstract_excerpt":"The recent advancement of Multimodal Large Language Models (MLLMs) has significantly improved their fine-grained perception of single images and general comprehension across multiple images. However, existing MLLMs still face challenges in achieving precise grounding in complex multi-image scenarios. To address this, we first explore a Chain-of-Thought (CoT) framework that integrates single-image grounding with multi-image comprehension. While partially effective, it remains unstable and struggles to capture abstract visual information due to its non-end-to-end nature. Therefore, we introduce "},"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":"2501.05767","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-10T07:56:23Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"0110453b6d89ab89bf018734ab40b96147c5b8bd763196929187d2590b33f6dc","abstract_canon_sha256":"d1eeaf63c430751886d0ac1a803ed635beebcedd69d4b3be4521fd8b0460ed05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:48.311225Z","signature_b64":"Add+9hlRbCm2qj745iRz6UOcu6x53VvcKhRzb/rWertliJAggGFo3GYO2hqtsP1EcSQnZDkRbdpIoS7mAmDBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76dfd5fe2c537ea0997dbcab23cf25472e6d30d17c0cdb6a5b2931160d8918ba","last_reissued_at":"2026-07-05T10:15:48.310709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:48.310709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Chao Huang, Chi Chen, Heyu Huang, Jinan Xu, Kaiyu Huang, Maosong Sun, Ruixuan Li, You Li, Yuhua Li, Zhiyuan Liu, Zonghao Guo","submitted_at":"2025-01-10T07:56:23Z","abstract_excerpt":"The recent advancement of Multimodal Large Language Models (MLLMs) has significantly improved their fine-grained perception of single images and general comprehension across multiple images. However, existing MLLMs still face challenges in achieving precise grounding in complex multi-image scenarios. To address this, we first explore a Chain-of-Thought (CoT) framework that integrates single-image grounding with multi-image comprehension. While partially effective, it remains unstable and struggles to capture abstract visual information due to its non-end-to-end nature. Therefore, we introduce "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05767","kind":"arxiv","version":3},"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/2501.05767/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":"2501.05767","created_at":"2026-07-05T10:15:48.310777+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05767v3","created_at":"2026-07-05T10:15:48.310777+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05767","created_at":"2026-07-05T10:15:48.310777+00:00"},{"alias_kind":"pith_short_12","alias_value":"O3P5L7RMKN7K","created_at":"2026-07-05T10:15:48.310777+00:00"},{"alias_kind":"pith_short_16","alias_value":"O3P5L7RMKN7KBGL5","created_at":"2026-07-05T10:15:48.310777+00:00"},{"alias_kind":"pith_short_8","alias_value":"O3P5L7RM","created_at":"2026-07-05T10:15:48.310777+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"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":159,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26602","citing_title":"DiCoBench: Benchmarking Multi-Image Fine-Grained Perception via Differential and Commonality Visual Cues","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25437","citing_title":"Does Seeing More Mean Knowing More? Mono-Anchored Advantage Normalization for Multi-Source Visual Reasoning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00748","citing_title":"Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2512.08980","citing_title":"Training Multi-Image Vision Agents via End2End Reinforcement Learning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22498","citing_title":"CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O3P5L7RMKN7KBGL5XSVSHTZFI4","json":"https://pith.science/pith/O3P5L7RMKN7KBGL5XSVSHTZFI4.json","graph_json":"https://pith.science/api/pith-number/O3P5L7RMKN7KBGL5XSVSHTZFI4/graph.json","events_json":"https://pith.science/api/pith-number/O3P5L7RMKN7KBGL5XSVSHTZFI4/events.json","paper":"https://pith.science/paper/O3P5L7RM"},"agent_actions":{"view_html":"https://pith.science/pith/O3P5L7RMKN7KBGL5XSVSHTZFI4","download_json":"https://pith.science/pith/O3P5L7RMKN7KBGL5XSVSHTZFI4.json","view_paper":"https://pith.science/paper/O3P5L7RM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05767&json=true","fetch_graph":"https://pith.science/api/pith-number/O3P5L7RMKN7KBGL5XSVSHTZFI4/graph.json","fetch_events":"https://pith.science/api/pith-number/O3P5L7RMKN7KBGL5XSVSHTZFI4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O3P5L7RMKN7KBGL5XSVSHTZFI4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O3P5L7RMKN7KBGL5XSVSHTZFI4/action/storage_attestation","attest_author":"https://pith.science/pith/O3P5L7RMKN7KBGL5XSVSHTZFI4/action/author_attestation","sign_citation":"https://pith.science/pith/O3P5L7RMKN7KBGL5XSVSHTZFI4/action/citation_signature","submit_replication":"https://pith.science/pith/O3P5L7RMKN7KBGL5XSVSHTZFI4/action/replication_record"}},"created_at":"2026-07-05T10:15:48.310777+00:00","updated_at":"2026-07-05T10:15:48.310777+00:00"}