{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VQFPYMTY4WGRVXXHEWI3HRQAC2","short_pith_number":"pith:VQFPYMTY","schema_version":"1.0","canonical_sha256":"ac0afc3278e58d1adee72591b3c6001694212189e5f52ccc1f05310c974c13ff","source":{"kind":"arxiv","id":"2310.07704","version":1},"attestation_state":"computed","paper":{"title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Ferret unifies referring and grounding in multimodal LLMs via a hybrid region representation of coordinates and continuous features.","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Haotian Zhang, Haoxuan You, Liangliang Cao, Shih-Fu Chang, Xianzhi Du, Yinfei Yang, Zhe Gan, Zirui Wang","submitted_at":"2023-10-11T17:55:15Z","abstract_excerpt":"We introduce Ferret, a new Multimodal Large Language Model (MLLM) capable of understanding spatial referring of any shape or granularity within an image and accurately grounding open-vocabulary descriptions. To unify referring and grounding in the LLM paradigm, Ferret employs a novel and powerful hybrid region representation that integrates discrete coordinates and continuous features jointly to represent a region in the image. To extract the continuous features of versatile regions, we propose a spatial-aware visual sampler, adept at handling varying sparsity across different shapes. Conseque"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2310.07704","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T17:55:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e0f7ae8a85a0a0fb3081cee3c416f47a53ccb17e4f03f15ee206de24cb7bc640","abstract_canon_sha256":"419cebae751a0f18a1d1ab104687a18f345ab96416311add427dc504104289dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:52.676408Z","signature_b64":"KTAu5voOn/Exa9UjFyZ+wKHJxEuJSEFZh0/jDi4NtUjqvLnt9mZTELxxUxiCiYho85XyLgDpdJkfEon00/gnDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac0afc3278e58d1adee72591b3c6001694212189e5f52ccc1f05310c974c13ff","last_reissued_at":"2026-05-17T23:38:52.675730Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:52.675730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Ferret unifies referring and grounding in multimodal LLMs via a hybrid region representation of coordinates and continuous features.","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Haotian Zhang, Haoxuan You, Liangliang Cao, Shih-Fu Chang, Xianzhi Du, Yinfei Yang, Zhe Gan, Zirui Wang","submitted_at":"2023-10-11T17:55:15Z","abstract_excerpt":"We introduce Ferret, a new Multimodal Large Language Model (MLLM) capable of understanding spatial referring of any shape or granularity within an image and accurately grounding open-vocabulary descriptions. To unify referring and grounding in the LLM paradigm, Ferret employs a novel and powerful hybrid region representation that integrates discrete coordinates and continuous features jointly to represent a region in the image. To extract the continuous features of versatile regions, we propose a spatial-aware visual sampler, adept at handling varying sparsity across different shapes. Conseque"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The resulting model not only achieves superior performance in classical referring and grounding tasks, but also greatly outperforms existing MLLMs in region-based and localization-demanded multimodal chatting.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the spatial-aware visual sampler can reliably extract continuous features from regions of arbitrary shape and sparsity without introducing systematic bias or information loss that would affect downstream grounding accuracy.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Ferret introduces a hybrid region representation and the GRIT dataset to let MLLMs refer to and ground arbitrary image regions, outperforming prior models on referring, grounding, and localization-aware chatting while reducing object hallucination.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Ferret unifies referring and grounding in multimodal LLMs via a hybrid region representation of coordinates and continuous features.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"73a4e79f223b2e942c9dc25ab4e1a885e1134543daecb2348e8939682c1a03a5"},"source":{"id":"2310.07704","kind":"arxiv","version":1},"verdict":{"id":"657af406-82d9-4462-a844-036903d1320e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T11:24:46.089802Z","strongest_claim":"The resulting model not only achieves superior performance in classical referring and grounding tasks, but also greatly outperforms existing MLLMs in region-based and localization-demanded multimodal chatting.","one_line_summary":"Ferret introduces a hybrid region representation and the GRIT dataset to let MLLMs refer to and ground arbitrary image regions, outperforming prior models on referring, grounding, and localization-aware chatting while reducing object hallucination.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the spatial-aware visual sampler can reliably extract continuous features from regions of arbitrary shape and sparsity without introducing systematic bias or information loss that would affect downstream grounding accuracy.","pith_extraction_headline":"Ferret unifies referring and grounding in multimodal LLMs via a hybrid region representation of coordinates and continuous features."},"references":{"count":20,"sample":[{"doi":"","year":null,"title":"The length of the output list needs to be exactly equal to the input list","work_id":"5df37ad1-a803-4193-87c3-dab4bc212ed9","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Do not explain the reasons","work_id":"eff2168b-1779-4d8a-a995-c2290e9a4073","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Do not mention the input entities, at least the output name and input name needs to be different","work_id":"a08ad987-d7c3-4b1f-8e9d-7bc6fe9b579a","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Do not mention something abstract, like ¨alien¨","work_id":"c210e3f5-c95a-4540-a7cc-786189f56aac","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"When dealing with quantities, focus solely on increasing the numbers during revision","work_id":"b1ce2dc5-9cf0-4e5d-83d1-16bcf11a63cc","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":20,"snapshot_sha256":"a7ededc6035b60c8027ce87beee2e525dbb4657e9dec9803222aae38e0150bb4","internal_anchors":0},"formal_canon":{"evidence_count":1,"snapshot_sha256":"135267e8810624bb106e0dc58d9ed73e308a9c2616ed8a4aa8c0277ed3d57860"},"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":"2310.07704","created_at":"2026-05-17T23:38:52.675849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07704v1","created_at":"2026-05-17T23:38:52.675849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07704","created_at":"2026-05-17T23:38:52.675849+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQFPYMTY4WGR","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQFPYMTY4WGRVXXH","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQFPYMTY","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":28,"internal_anchor_count":28,"sample":[{"citing_arxiv_id":"2412.18158","citing_title":"Semantics Disentanglement and Composition for Universal Image Coding with Efficiently LLM Reasoning and Generative Diffusion","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2505.15616","citing_title":"LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18018","citing_title":"See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding","ref_index":85,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16903","citing_title":"WOW-Seg: A Word-free Open World Segmentation Model","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2512.10554","citing_title":"Grounding Everything in Tokens for Multimodal Large Language Models","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":143,"is_internal_anchor":true},{"citing_arxiv_id":"2401.01614","citing_title":"GPT-4V(ision) is a Generalist Web Agent, if Grounded","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2311.03079","citing_title":"CogVLM: Visual Expert for Pretrained Language Models","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2603.14882","citing_title":"LLMind: Bio-inspired Training-free Adaptive Visual Representations for Vision-Language Models","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2409.17146","citing_title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","ref_index":125,"is_internal_anchor":true},{"citing_arxiv_id":"2603.27507","citing_title":"Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12882","citing_title":"CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2604.00270","citing_title":"OmniSch: A Multimodal PCB Schematic Benchmark For Structured Diagram Visual Reasoning","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2402.00253","citing_title":"A Survey on Hallucination in Large Vision-Language Models","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11591","citing_title":"Logit-Attention Divergence: Mitigating Position Bias in Multi-Image Retrieval via Attention-Guided Calibration","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22498","citing_title":"CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01391","citing_title":"VISTA: Video Interaction Spatio-Temporal Analysis Benchmark","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00663","citing_title":"Affordance Agent Harness: Verification-Gated Skill Orchestration","ref_index":80,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00891","citing_title":"X2SAM: Any Segmentation in Images and Videos","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00905","citing_title":"DIAGRAMS: A Review Framework for Reasoning-Level Attribution in Diagram QA","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11789","citing_title":"LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation","ref_index":212,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10527","citing_title":"STORM: End-to-End Referring Multi-Object Tracking in Videos","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00663","citing_title":"Affordance Agent Harness: Verification-Gated Skill Orchestration","ref_index":80,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07141","citing_title":"Qwen3-VL-Seg: Unlocking Open-World Referring Segmentation with Vision-Language Grounding","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10060","citing_title":"Mosaic: Cross-Modal Clustering for Efficient Video Understanding","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQFPYMTY4WGRVXXHEWI3HRQAC2","json":"https://pith.science/pith/VQFPYMTY4WGRVXXHEWI3HRQAC2.json","graph_json":"https://pith.science/api/pith-number/VQFPYMTY4WGRVXXHEWI3HRQAC2/graph.json","events_json":"https://pith.science/api/pith-number/VQFPYMTY4WGRVXXHEWI3HRQAC2/events.json","paper":"https://pith.science/paper/VQFPYMTY"},"agent_actions":{"view_html":"https://pith.science/pith/VQFPYMTY4WGRVXXHEWI3HRQAC2","download_json":"https://pith.science/pith/VQFPYMTY4WGRVXXHEWI3HRQAC2.json","view_paper":"https://pith.science/paper/VQFPYMTY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07704&json=true","fetch_graph":"https://pith.science/api/pith-number/VQFPYMTY4WGRVXXHEWI3HRQAC2/graph.json","fetch_events":"https://pith.science/api/pith-number/VQFPYMTY4WGRVXXHEWI3HRQAC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQFPYMTY4WGRVXXHEWI3HRQAC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQFPYMTY4WGRVXXHEWI3HRQAC2/action/storage_attestation","attest_author":"https://pith.science/pith/VQFPYMTY4WGRVXXHEWI3HRQAC2/action/author_attestation","sign_citation":"https://pith.science/pith/VQFPYMTY4WGRVXXHEWI3HRQAC2/action/citation_signature","submit_replication":"https://pith.science/pith/VQFPYMTY4WGRVXXHEWI3HRQAC2/action/replication_record"}},"created_at":"2026-05-17T23:38:52.675849+00:00","updated_at":"2026-05-17T23:38:52.675849+00:00"}