{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NOEBP4JEAST6A5LXT6SMTXCC6V","short_pith_number":"pith:NOEBP4JE","schema_version":"1.0","canonical_sha256":"6b8817f12404a7e075779fa4c9dc42f546e792a63dfab6956c070aaffa899d45","source":{"kind":"arxiv","id":"2403.02969","version":2},"attestation_state":"computed","paper":{"title":"Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Luo, Huchuan Lu, Jin-Peng Lan, Junwen He, Jun-Yan He, Lijun Wang, Xuansong Xie, Yifan Wang","submitted_at":"2024-03-05T13:45:46Z","abstract_excerpt":"Multimodal Large Language Model (MLLMs) leverages Large Language Models as a cognitive framework for diverse visual-language tasks. Recent efforts have been made to equip MLLMs with visual perceiving and grounding capabilities. However, there still remains a gap in providing fine-grained pixel-level perceptions and extending interactions beyond text-specific inputs. In this work, we propose {\\bf{AnyRef}}, a general MLLM model that can generate pixel-wise object perceptions and natural language descriptions from multi-modality references, such as texts, boxes, images, or audio. This innovation "},"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":"2403.02969","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T13:45:46Z","cross_cats_sorted":[],"title_canon_sha256":"aaf0d86f16d7973a581c07171cd04d058af2cd5dfb4f3738b22d0591e0998980","abstract_canon_sha256":"fe7889df4d4cd57a994f91d9311631d65d82641ada27db56949ecb7bb3fe638a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:02.557617Z","signature_b64":"z4l1OrM5jJUcIDyu5dpryLqqFqGhYg8e4iZ8+sGpw+Sgs5qyW3CIpPvw/h45u9Ml8ow1FEw/I/LICcOhlWeGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b8817f12404a7e075779fa4c9dc42f546e792a63dfab6956c070aaffa899d45","last_reissued_at":"2026-07-05T08:00:02.557013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:02.557013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Luo, Huchuan Lu, Jin-Peng Lan, Junwen He, Jun-Yan He, Lijun Wang, Xuansong Xie, Yifan Wang","submitted_at":"2024-03-05T13:45:46Z","abstract_excerpt":"Multimodal Large Language Model (MLLMs) leverages Large Language Models as a cognitive framework for diverse visual-language tasks. Recent efforts have been made to equip MLLMs with visual perceiving and grounding capabilities. However, there still remains a gap in providing fine-grained pixel-level perceptions and extending interactions beyond text-specific inputs. In this work, we propose {\\bf{AnyRef}}, a general MLLM model that can generate pixel-wise object perceptions and natural language descriptions from multi-modality references, such as texts, boxes, images, or audio. This innovation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02969","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/2403.02969/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":"2403.02969","created_at":"2026-07-05T08:00:02.557093+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02969v2","created_at":"2026-07-05T08:00:02.557093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02969","created_at":"2026-07-05T08:00:02.557093+00:00"},{"alias_kind":"pith_short_12","alias_value":"NOEBP4JEAST6","created_at":"2026-07-05T08:00:02.557093+00:00"},{"alias_kind":"pith_short_16","alias_value":"NOEBP4JEAST6A5LX","created_at":"2026-07-05T08:00:02.557093+00:00"},{"alias_kind":"pith_short_8","alias_value":"NOEBP4JE","created_at":"2026-07-05T08:00:02.557093+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NOEBP4JEAST6A5LXT6SMTXCC6V","json":"https://pith.science/pith/NOEBP4JEAST6A5LXT6SMTXCC6V.json","graph_json":"https://pith.science/api/pith-number/NOEBP4JEAST6A5LXT6SMTXCC6V/graph.json","events_json":"https://pith.science/api/pith-number/NOEBP4JEAST6A5LXT6SMTXCC6V/events.json","paper":"https://pith.science/paper/NOEBP4JE"},"agent_actions":{"view_html":"https://pith.science/pith/NOEBP4JEAST6A5LXT6SMTXCC6V","download_json":"https://pith.science/pith/NOEBP4JEAST6A5LXT6SMTXCC6V.json","view_paper":"https://pith.science/paper/NOEBP4JE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02969&json=true","fetch_graph":"https://pith.science/api/pith-number/NOEBP4JEAST6A5LXT6SMTXCC6V/graph.json","fetch_events":"https://pith.science/api/pith-number/NOEBP4JEAST6A5LXT6SMTXCC6V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NOEBP4JEAST6A5LXT6SMTXCC6V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NOEBP4JEAST6A5LXT6SMTXCC6V/action/storage_attestation","attest_author":"https://pith.science/pith/NOEBP4JEAST6A5LXT6SMTXCC6V/action/author_attestation","sign_citation":"https://pith.science/pith/NOEBP4JEAST6A5LXT6SMTXCC6V/action/citation_signature","submit_replication":"https://pith.science/pith/NOEBP4JEAST6A5LXT6SMTXCC6V/action/replication_record"}},"created_at":"2026-07-05T08:00:02.557093+00:00","updated_at":"2026-07-05T08:00:02.557093+00:00"}