{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KSKEYKYPGFBNJUHOSHCB3UD3QI","short_pith_number":"pith:KSKEYKYP","schema_version":"1.0","canonical_sha256":"54944c2b0f3142d4d0ee91c41dd07b8233bf5a5bfe83d984790e14d38ae989ab","source":{"kind":"arxiv","id":"2308.07891","version":1},"attestation_state":"computed","paper":{"title":"Link-Context Learning for Multimodal LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Feng Zhu, Rui Zhao, Weichen Fan, Yan Tai, Zhao Zhang, Ziwei Liu","submitted_at":"2023-08-15T17:33:24Z","abstract_excerpt":"The ability to learn from context with novel concepts, and deliver appropriate responses are essential in human conversations. Despite current Multimodal Large Language Models (MLLMs) and Large Language Models (LLMs) being trained on mega-scale datasets, recognizing unseen images or understanding novel concepts in a training-free manner remains a challenge. In-Context Learning (ICL) explores training-free few-shot learning, where models are encouraged to ``learn to learn\" from limited tasks and generalize to unseen tasks. In this work, we propose link-context learning (LCL), which emphasizes \""},"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":"2308.07891","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-15T17:33:24Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"42dd3e206eba93611141d30a2ce1bdb9fe36ae41569a32e65df7df1f2173a461","abstract_canon_sha256":"080d317baf1103479ff4c06bced57d3f45abb9b9729365a88c15c21f097218d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:32.963298Z","signature_b64":"lqCgtH3VodgFCRp8OX+5yRqEO/ldw9H3DRkwhv6PcBCLf+EVzqPuA4ZeSO2JqOtFete0ij2X80FuAbIoJiIMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54944c2b0f3142d4d0ee91c41dd07b8233bf5a5bfe83d984790e14d38ae989ab","last_reissued_at":"2026-07-05T06:41:32.962802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:32.962802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Link-Context Learning for Multimodal LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Feng Zhu, Rui Zhao, Weichen Fan, Yan Tai, Zhao Zhang, Ziwei Liu","submitted_at":"2023-08-15T17:33:24Z","abstract_excerpt":"The ability to learn from context with novel concepts, and deliver appropriate responses are essential in human conversations. Despite current Multimodal Large Language Models (MLLMs) and Large Language Models (LLMs) being trained on mega-scale datasets, recognizing unseen images or understanding novel concepts in a training-free manner remains a challenge. In-Context Learning (ICL) explores training-free few-shot learning, where models are encouraged to ``learn to learn\" from limited tasks and generalize to unseen tasks. In this work, we propose link-context learning (LCL), which emphasizes \""},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.07891","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/2308.07891/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":"2308.07891","created_at":"2026-07-05T06:41:32.962865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.07891v1","created_at":"2026-07-05T06:41:32.962865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.07891","created_at":"2026-07-05T06:41:32.962865+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSKEYKYPGFBN","created_at":"2026-07-05T06:41:32.962865+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSKEYKYPGFBNJUHO","created_at":"2026-07-05T06:41:32.962865+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSKEYKYP","created_at":"2026-07-05T06:41:32.962865+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":177,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18562","citing_title":"AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation","ref_index":173,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KSKEYKYPGFBNJUHOSHCB3UD3QI","json":"https://pith.science/pith/KSKEYKYPGFBNJUHOSHCB3UD3QI.json","graph_json":"https://pith.science/api/pith-number/KSKEYKYPGFBNJUHOSHCB3UD3QI/graph.json","events_json":"https://pith.science/api/pith-number/KSKEYKYPGFBNJUHOSHCB3UD3QI/events.json","paper":"https://pith.science/paper/KSKEYKYP"},"agent_actions":{"view_html":"https://pith.science/pith/KSKEYKYPGFBNJUHOSHCB3UD3QI","download_json":"https://pith.science/pith/KSKEYKYPGFBNJUHOSHCB3UD3QI.json","view_paper":"https://pith.science/paper/KSKEYKYP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.07891&json=true","fetch_graph":"https://pith.science/api/pith-number/KSKEYKYPGFBNJUHOSHCB3UD3QI/graph.json","fetch_events":"https://pith.science/api/pith-number/KSKEYKYPGFBNJUHOSHCB3UD3QI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSKEYKYPGFBNJUHOSHCB3UD3QI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSKEYKYPGFBNJUHOSHCB3UD3QI/action/storage_attestation","attest_author":"https://pith.science/pith/KSKEYKYPGFBNJUHOSHCB3UD3QI/action/author_attestation","sign_citation":"https://pith.science/pith/KSKEYKYPGFBNJUHOSHCB3UD3QI/action/citation_signature","submit_replication":"https://pith.science/pith/KSKEYKYPGFBNJUHOSHCB3UD3QI/action/replication_record"}},"created_at":"2026-07-05T06:41:32.962865+00:00","updated_at":"2026-07-05T06:41:32.962865+00:00"}