{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5XHZ5WWSO7DUOILJNPHHBHXY75","short_pith_number":"pith:5XHZ5WWS","schema_version":"1.0","canonical_sha256":"edcf9edad277c74721696bce709ef8ff73759e3c65f6e0b6f985ea841cea00cc","source":{"kind":"arxiv","id":"2406.13185","version":3},"attestation_state":"computed","paper":{"title":"LIVE: Learnable In-Context Vector for Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenduo Hao, Jiawei Peng, Xin Geng, Xinting Hu, Xu Yang, Yingzhe Peng","submitted_at":"2024-06-19T03:33:45Z","abstract_excerpt":"As language models continue to scale, Large Language Models (LLMs) have exhibited emerging capabilities in In-Context Learning (ICL), enabling them to solve language tasks by prefixing a few in-context demonstrations (ICDs) as context. Inspired by these advancements, researchers have extended these techniques to develop Large Multimodal Models (LMMs) with ICL capabilities. However, applying ICL usually faces two major challenges: 1) using more ICDs will largely increase the inference time and 2) the performance is sensitive to the selection of ICDs. These challenges are further exacerbated in "},"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":"2406.13185","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T03:33:45Z","cross_cats_sorted":[],"title_canon_sha256":"8ee2f7811b80b5d7ecb4e0df7f86501046658f7272a8c79c90b7dcd6a8e63d70","abstract_canon_sha256":"c79af63b940af6a1d8e29f93e8d33d04ad1029962fe3afdeb9e117031e9ffe12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:51.871377Z","signature_b64":"te6Gz+DltN/Yj66EjYK8FcC0N8YTRT9ZoHWNPMKAuZMeNORjtEt6gNby6FzZvW8l7VrBhamOS7K/uk4OhaFvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edcf9edad277c74721696bce709ef8ff73759e3c65f6e0b6f985ea841cea00cc","last_reissued_at":"2026-07-05T09:28:51.870884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:51.870884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LIVE: Learnable In-Context Vector for Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenduo Hao, Jiawei Peng, Xin Geng, Xinting Hu, Xu Yang, Yingzhe Peng","submitted_at":"2024-06-19T03:33:45Z","abstract_excerpt":"As language models continue to scale, Large Language Models (LLMs) have exhibited emerging capabilities in In-Context Learning (ICL), enabling them to solve language tasks by prefixing a few in-context demonstrations (ICDs) as context. Inspired by these advancements, researchers have extended these techniques to develop Large Multimodal Models (LMMs) with ICL capabilities. However, applying ICL usually faces two major challenges: 1) using more ICDs will largely increase the inference time and 2) the performance is sensitive to the selection of ICDs. These challenges are further exacerbated in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13185","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/2406.13185/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":"2406.13185","created_at":"2026-07-05T09:28:51.870934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13185v3","created_at":"2026-07-05T09:28:51.870934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13185","created_at":"2026-07-05T09:28:51.870934+00:00"},{"alias_kind":"pith_short_12","alias_value":"5XHZ5WWSO7DU","created_at":"2026-07-05T09:28:51.870934+00:00"},{"alias_kind":"pith_short_16","alias_value":"5XHZ5WWSO7DUOILJ","created_at":"2026-07-05T09:28:51.870934+00:00"},{"alias_kind":"pith_short_8","alias_value":"5XHZ5WWS","created_at":"2026-07-05T09:28:51.870934+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27194","citing_title":"Not All Tokens Matter Equally: Dynamic In-context Vector Distillation with Decisive-Token Supervision for Long-form Medical Report Generation","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5XHZ5WWSO7DUOILJNPHHBHXY75","json":"https://pith.science/pith/5XHZ5WWSO7DUOILJNPHHBHXY75.json","graph_json":"https://pith.science/api/pith-number/5XHZ5WWSO7DUOILJNPHHBHXY75/graph.json","events_json":"https://pith.science/api/pith-number/5XHZ5WWSO7DUOILJNPHHBHXY75/events.json","paper":"https://pith.science/paper/5XHZ5WWS"},"agent_actions":{"view_html":"https://pith.science/pith/5XHZ5WWSO7DUOILJNPHHBHXY75","download_json":"https://pith.science/pith/5XHZ5WWSO7DUOILJNPHHBHXY75.json","view_paper":"https://pith.science/paper/5XHZ5WWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13185&json=true","fetch_graph":"https://pith.science/api/pith-number/5XHZ5WWSO7DUOILJNPHHBHXY75/graph.json","fetch_events":"https://pith.science/api/pith-number/5XHZ5WWSO7DUOILJNPHHBHXY75/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5XHZ5WWSO7DUOILJNPHHBHXY75/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5XHZ5WWSO7DUOILJNPHHBHXY75/action/storage_attestation","attest_author":"https://pith.science/pith/5XHZ5WWSO7DUOILJNPHHBHXY75/action/author_attestation","sign_citation":"https://pith.science/pith/5XHZ5WWSO7DUOILJNPHHBHXY75/action/citation_signature","submit_replication":"https://pith.science/pith/5XHZ5WWSO7DUOILJNPHHBHXY75/action/replication_record"}},"created_at":"2026-07-05T09:28:51.870934+00:00","updated_at":"2026-07-05T09:28:51.870934+00:00"}