{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WBOCGK55QSQHIDW3BY7ZUWNQNF","short_pith_number":"pith:WBOCGK55","schema_version":"1.0","canonical_sha256":"b05c232bbd84a0740edb0e3f9a59b0694b997c3a8062859973861ac35c1ba3ec","source":{"kind":"arxiv","id":"2403.20271","version":3},"attestation_state":"computed","paper":{"title":"Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bocheng Zou, Hongsheng Li, Peng Gao, Ruichuan An, Shanghang Zhang, Siyuan Huang, Weifeng Lin, Xinyu Wei, Yulin Luo","submitted_at":"2024-03-29T16:26:20Z","abstract_excerpt":"In this paper, we present the Draw-and-Understand framework, exploring how to integrate visual prompting understanding capabilities into Multimodal Large Language Models (MLLMs). Visual prompts allow users to interact through multi-modal instructions, enhancing the models' interactivity and fine-grained image comprehension. In this framework, we propose a general architecture adaptable to different pre-trained MLLMs, enabling it to recognize various types of visual prompts (such as points, bounding boxes, and free-form shapes) alongside language understanding. Additionally, we introduce MDVP-I"},"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":"2403.20271","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-29T16:26:20Z","cross_cats_sorted":[],"title_canon_sha256":"9b2d57aca6d574777347802df8b9caa2dbed3dc68b4489b8f83896f5e840d796","abstract_canon_sha256":"775db813b1c577354b8423eadcdce0eff1100281b017220a78ef01c5f30246cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:08.193958Z","signature_b64":"yRpBu9VhObd2I0byq0DnU5qmUsdD7xbYUCt4rREAEKPcWpM/iF4MF5pCxkJ9pw+WR6T7DaD/a/F1W2XGXwHRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b05c232bbd84a0740edb0e3f9a59b0694b997c3a8062859973861ac35c1ba3ec","last_reissued_at":"2026-07-05T10:18:08.193499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:08.193499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bocheng Zou, Hongsheng Li, Peng Gao, Ruichuan An, Shanghang Zhang, Siyuan Huang, Weifeng Lin, Xinyu Wei, Yulin Luo","submitted_at":"2024-03-29T16:26:20Z","abstract_excerpt":"In this paper, we present the Draw-and-Understand framework, exploring how to integrate visual prompting understanding capabilities into Multimodal Large Language Models (MLLMs). Visual prompts allow users to interact through multi-modal instructions, enhancing the models' interactivity and fine-grained image comprehension. In this framework, we propose a general architecture adaptable to different pre-trained MLLMs, enabling it to recognize various types of visual prompts (such as points, bounding boxes, and free-form shapes) alongside language understanding. Additionally, we introduce MDVP-I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.20271","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/2403.20271/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":"2403.20271","created_at":"2026-07-05T10:18:08.193558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.20271v3","created_at":"2026-07-05T10:18:08.193558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.20271","created_at":"2026-07-05T10:18:08.193558+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBOCGK55QSQH","created_at":"2026-07-05T10:18:08.193558+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBOCGK55QSQHIDW3","created_at":"2026-07-05T10:18:08.193558+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBOCGK55","created_at":"2026-07-05T10:18:08.193558+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"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":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27365","citing_title":"LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16903","citing_title":"WOW-Seg: A Word-free Open World Segmentation Model","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2511.18957","citing_title":"Eevee: Towards Close-up High-resolution Video-based Virtual Try-on","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07348","citing_title":"MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2512.09299","citing_title":"VABench: A Comprehensive Benchmark for Audio-Video Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2602.03151","citing_title":"Enhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional Feature Restoration","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11789","citing_title":"LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2501.13106","citing_title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04838","citing_title":"Less Detail, Better Answers: Degradation-Driven Prompting for VQA","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WBOCGK55QSQHIDW3BY7ZUWNQNF","json":"https://pith.science/pith/WBOCGK55QSQHIDW3BY7ZUWNQNF.json","graph_json":"https://pith.science/api/pith-number/WBOCGK55QSQHIDW3BY7ZUWNQNF/graph.json","events_json":"https://pith.science/api/pith-number/WBOCGK55QSQHIDW3BY7ZUWNQNF/events.json","paper":"https://pith.science/paper/WBOCGK55"},"agent_actions":{"view_html":"https://pith.science/pith/WBOCGK55QSQHIDW3BY7ZUWNQNF","download_json":"https://pith.science/pith/WBOCGK55QSQHIDW3BY7ZUWNQNF.json","view_paper":"https://pith.science/paper/WBOCGK55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.20271&json=true","fetch_graph":"https://pith.science/api/pith-number/WBOCGK55QSQHIDW3BY7ZUWNQNF/graph.json","fetch_events":"https://pith.science/api/pith-number/WBOCGK55QSQHIDW3BY7ZUWNQNF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBOCGK55QSQHIDW3BY7ZUWNQNF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBOCGK55QSQHIDW3BY7ZUWNQNF/action/storage_attestation","attest_author":"https://pith.science/pith/WBOCGK55QSQHIDW3BY7ZUWNQNF/action/author_attestation","sign_citation":"https://pith.science/pith/WBOCGK55QSQHIDW3BY7ZUWNQNF/action/citation_signature","submit_replication":"https://pith.science/pith/WBOCGK55QSQHIDW3BY7ZUWNQNF/action/replication_record"}},"created_at":"2026-07-05T10:18:08.193558+00:00","updated_at":"2026-07-05T10:18:08.193558+00:00"}