{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HTS3IHCUMRQAXYUCG7LUAPMMFS","short_pith_number":"pith:HTS3IHCU","schema_version":"1.0","canonical_sha256":"3ce5b41c5464600be28237d7403d8c2cbd72db565952ab4110aa250e3f33b7db","source":{"kind":"arxiv","id":"2308.02299","version":1},"attestation_state":"computed","paper":{"title":"RegionBLIP: A Unified Multi-modal Pre-training Framework for Holistic and Regional Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaohui Yu, Fan Wang, Qiang Zhou, Shaofeng Zhang, Sitong Wu, Zhibing Wang","submitted_at":"2023-08-03T14:17:22Z","abstract_excerpt":"In this work, we investigate extending the comprehension of Multi-modal Large Language Models (MLLMs) to regional objects. To this end, we propose to extract features corresponding to regional objects as soft prompts for LLM, which provides a straightforward and scalable approach and eliminates the need for LLM fine-tuning. To effectively extract regional features from regular image features and irregular point cloud features, we present a novel and unified position-assisted feature extraction module. Furthermore, training an MLLM from scratch is highly time-consuming. Thus, we propose increme"},"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":"2308.02299","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-03T14:17:22Z","cross_cats_sorted":[],"title_canon_sha256":"b9bb585c7f0a7dd9219b477c15552af0cb78a55b5d34a3576ce5e7293d573062","abstract_canon_sha256":"4c31e90d2dd3f02b1a2c25d51c762990428ba222b23f9e3162baae3d29ff9053"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:40.886093Z","signature_b64":"SyJrTacxXnRDNI1MXiGQU2MDVkRH8HojrXQFmQx2ye/Qp3i+BERGLD8cXSvhOcK922AJYGUa9J1Q5cW/nb0WCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ce5b41c5464600be28237d7403d8c2cbd72db565952ab4110aa250e3f33b7db","last_reissued_at":"2026-07-05T06:37:40.885647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:40.885647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RegionBLIP: A Unified Multi-modal Pre-training Framework for Holistic and Regional Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaohui Yu, Fan Wang, Qiang Zhou, Shaofeng Zhang, Sitong Wu, Zhibing Wang","submitted_at":"2023-08-03T14:17:22Z","abstract_excerpt":"In this work, we investigate extending the comprehension of Multi-modal Large Language Models (MLLMs) to regional objects. To this end, we propose to extract features corresponding to regional objects as soft prompts for LLM, which provides a straightforward and scalable approach and eliminates the need for LLM fine-tuning. To effectively extract regional features from regular image features and irregular point cloud features, we present a novel and unified position-assisted feature extraction module. Furthermore, training an MLLM from scratch is highly time-consuming. Thus, we propose increme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.02299","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/2308.02299/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":"2308.02299","created_at":"2026-07-05T06:37:40.885700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.02299v1","created_at":"2026-07-05T06:37:40.885700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.02299","created_at":"2026-07-05T06:37:40.885700+00:00"},{"alias_kind":"pith_short_12","alias_value":"HTS3IHCUMRQA","created_at":"2026-07-05T06:37:40.885700+00:00"},{"alias_kind":"pith_short_16","alias_value":"HTS3IHCUMRQAXYUC","created_at":"2026-07-05T06:37:40.885700+00:00"},{"alias_kind":"pith_short_8","alias_value":"HTS3IHCU","created_at":"2026-07-05T06:37:40.885700+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/HTS3IHCUMRQAXYUCG7LUAPMMFS","json":"https://pith.science/pith/HTS3IHCUMRQAXYUCG7LUAPMMFS.json","graph_json":"https://pith.science/api/pith-number/HTS3IHCUMRQAXYUCG7LUAPMMFS/graph.json","events_json":"https://pith.science/api/pith-number/HTS3IHCUMRQAXYUCG7LUAPMMFS/events.json","paper":"https://pith.science/paper/HTS3IHCU"},"agent_actions":{"view_html":"https://pith.science/pith/HTS3IHCUMRQAXYUCG7LUAPMMFS","download_json":"https://pith.science/pith/HTS3IHCUMRQAXYUCG7LUAPMMFS.json","view_paper":"https://pith.science/paper/HTS3IHCU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.02299&json=true","fetch_graph":"https://pith.science/api/pith-number/HTS3IHCUMRQAXYUCG7LUAPMMFS/graph.json","fetch_events":"https://pith.science/api/pith-number/HTS3IHCUMRQAXYUCG7LUAPMMFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HTS3IHCUMRQAXYUCG7LUAPMMFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HTS3IHCUMRQAXYUCG7LUAPMMFS/action/storage_attestation","attest_author":"https://pith.science/pith/HTS3IHCUMRQAXYUCG7LUAPMMFS/action/author_attestation","sign_citation":"https://pith.science/pith/HTS3IHCUMRQAXYUCG7LUAPMMFS/action/citation_signature","submit_replication":"https://pith.science/pith/HTS3IHCUMRQAXYUCG7LUAPMMFS/action/replication_record"}},"created_at":"2026-07-05T06:37:40.885700+00:00","updated_at":"2026-07-05T06:37:40.885700+00:00"}