{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RO7ZSOQSVLLAOI3ULOYF3JCUBX","short_pith_number":"pith:RO7ZSOQS","schema_version":"1.0","canonical_sha256":"8bbf993a12aad60723745bb05da4540dd36eb5516ac831a28d2c2c6e6f6d6bc8","source":{"kind":"arxiv","id":"2409.15310","version":1},"attestation_state":"computed","paper":{"title":"Visual Prompting in Multimodal Large Language Models: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Aaron Chang, Dimitris N. Metaxas, Jingbo Shang, Julian McAuley, Junda Wu, Lina Yao, Ruiyi Zhang, Ryan A. Rossi, Subrata Mitra, Sungchul Kim, Tong Yu, Xintong Li, Yu Xia, Zhaoyang Xia, Zhehao Zhang","submitted_at":"2024-09-05T08:47:34Z","abstract_excerpt":"Multimodal large language models (MLLMs) equip pre-trained large-language models (LLMs) with visual capabilities. While textual prompting in LLMs has been widely studied, visual prompting has emerged for more fine-grained and free-form visual instructions. This paper presents the first comprehensive survey on visual prompting methods in MLLMs, focusing on visual prompting, prompt generation, compositional reasoning, and prompt learning. We categorize existing visual prompts and discuss generative methods for automatic prompt annotations on the images. We also examine visual prompting methods t"},"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":"2409.15310","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-05T08:47:34Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6187fa1658cd86c4d7c6f9c4933b0e5fdbc901fb7e9072c5f04f6350b9d933ee","abstract_canon_sha256":"d23fbd30424d6c00a2796d46cd5d6439c1c79a636412e269b93d2e1ff924fa0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:52.763617Z","signature_b64":"p7UGl8oNf0gwJK2HUGYsaEHEo/s8XGHN2M7Uuky4/lnwTdOdXysSsb58bS6yQabSYuLffBzD4j4lZ2SZHOHRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bbf993a12aad60723745bb05da4540dd36eb5516ac831a28d2c2c6e6f6d6bc8","last_reissued_at":"2026-07-05T09:10:52.762781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:52.762781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Prompting in Multimodal Large Language Models: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Aaron Chang, Dimitris N. Metaxas, Jingbo Shang, Julian McAuley, Junda Wu, Lina Yao, Ruiyi Zhang, Ryan A. Rossi, Subrata Mitra, Sungchul Kim, Tong Yu, Xintong Li, Yu Xia, Zhaoyang Xia, Zhehao Zhang","submitted_at":"2024-09-05T08:47:34Z","abstract_excerpt":"Multimodal large language models (MLLMs) equip pre-trained large-language models (LLMs) with visual capabilities. While textual prompting in LLMs has been widely studied, visual prompting has emerged for more fine-grained and free-form visual instructions. This paper presents the first comprehensive survey on visual prompting methods in MLLMs, focusing on visual prompting, prompt generation, compositional reasoning, and prompt learning. We categorize existing visual prompts and discuss generative methods for automatic prompt annotations on the images. We also examine visual prompting methods t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15310","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/2409.15310/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":"2409.15310","created_at":"2026-07-05T09:10:52.763070+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.15310v1","created_at":"2026-07-05T09:10:52.763070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15310","created_at":"2026-07-05T09:10:52.763070+00:00"},{"alias_kind":"pith_short_12","alias_value":"RO7ZSOQSVLLA","created_at":"2026-07-05T09:10:52.763070+00:00"},{"alias_kind":"pith_short_16","alias_value":"RO7ZSOQSVLLAOI3U","created_at":"2026-07-05T09:10:52.763070+00:00"},{"alias_kind":"pith_short_8","alias_value":"RO7ZSOQS","created_at":"2026-07-05T09:10:52.763070+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15342","citing_title":"Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11169","citing_title":"OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08526","citing_title":"Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10527","citing_title":"STORM: End-to-End Referring Multi-Object Tracking in Videos","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08846","citing_title":"Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02913","citing_title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","ref_index":137,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16993","citing_title":"Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RO7ZSOQSVLLAOI3ULOYF3JCUBX","json":"https://pith.science/pith/RO7ZSOQSVLLAOI3ULOYF3JCUBX.json","graph_json":"https://pith.science/api/pith-number/RO7ZSOQSVLLAOI3ULOYF3JCUBX/graph.json","events_json":"https://pith.science/api/pith-number/RO7ZSOQSVLLAOI3ULOYF3JCUBX/events.json","paper":"https://pith.science/paper/RO7ZSOQS"},"agent_actions":{"view_html":"https://pith.science/pith/RO7ZSOQSVLLAOI3ULOYF3JCUBX","download_json":"https://pith.science/pith/RO7ZSOQSVLLAOI3ULOYF3JCUBX.json","view_paper":"https://pith.science/paper/RO7ZSOQS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.15310&json=true","fetch_graph":"https://pith.science/api/pith-number/RO7ZSOQSVLLAOI3ULOYF3JCUBX/graph.json","fetch_events":"https://pith.science/api/pith-number/RO7ZSOQSVLLAOI3ULOYF3JCUBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RO7ZSOQSVLLAOI3ULOYF3JCUBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RO7ZSOQSVLLAOI3ULOYF3JCUBX/action/storage_attestation","attest_author":"https://pith.science/pith/RO7ZSOQSVLLAOI3ULOYF3JCUBX/action/author_attestation","sign_citation":"https://pith.science/pith/RO7ZSOQSVLLAOI3ULOYF3JCUBX/action/citation_signature","submit_replication":"https://pith.science/pith/RO7ZSOQSVLLAOI3ULOYF3JCUBX/action/replication_record"}},"created_at":"2026-07-05T09:10:52.763070+00:00","updated_at":"2026-07-05T09:10:52.763070+00:00"}