{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XQYCD3ZNLJEUCWE2ZCP3BTEJWM","short_pith_number":"pith:XQYCD3ZN","schema_version":"1.0","canonical_sha256":"bc3021ef2d5a4941589ac89fb0cc89b33f7b15633b56ce47cf8f72c369c43383","source":{"kind":"arxiv","id":"2402.07398","version":3},"attestation_state":"computed","paper":{"title":"VisLingInstruct: Elevating Zero-Shot Learning in Multi-Modal Language Models with Autonomous Instruction Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dawei Yin, Dongsheng Zhu, Guoliang Xing, Jinghui Lu, Junfeng Wang, Weidong Han, Xunzhu Tang, Yukun Zhao","submitted_at":"2024-02-12T04:13:16Z","abstract_excerpt":"This paper presents VisLingInstruct, a novel approach to advancing Multi-Modal Language Models (MMLMs) in zero-shot learning. Current MMLMs show impressive zero-shot abilities in multi-modal tasks, but their performance depends heavily on the quality of instructions. VisLingInstruct tackles this by autonomously evaluating and optimizing instructional texts through In-Context Learning, improving the synergy between visual perception and linguistic expression in MMLMs. Alongside this instructional advancement, we have also optimized the visual feature extraction modules in MMLMs, further augment"},"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":"2402.07398","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-12T04:13:16Z","cross_cats_sorted":[],"title_canon_sha256":"fb887ebb38468038280103c67a45035ccaab01fcd7c38a8342302f335e8683af","abstract_canon_sha256":"d45783a6c2174f016f74b5e358d50335864c1fbde9f8126fc0af936563ba8c6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:47.324946Z","signature_b64":"u8EEd86RlQ8iEpWAnv6M48/gXIM9vWhbVi25CAvqDiW0ArECEc7pBUhoOxVOUSXcYBNcyxxtwbVUsgBCymj1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc3021ef2d5a4941589ac89fb0cc89b33f7b15633b56ce47cf8f72c369c43383","last_reissued_at":"2026-07-05T08:34:47.324483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:47.324483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisLingInstruct: Elevating Zero-Shot Learning in Multi-Modal Language Models with Autonomous Instruction Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dawei Yin, Dongsheng Zhu, Guoliang Xing, Jinghui Lu, Junfeng Wang, Weidong Han, Xunzhu Tang, Yukun Zhao","submitted_at":"2024-02-12T04:13:16Z","abstract_excerpt":"This paper presents VisLingInstruct, a novel approach to advancing Multi-Modal Language Models (MMLMs) in zero-shot learning. Current MMLMs show impressive zero-shot abilities in multi-modal tasks, but their performance depends heavily on the quality of instructions. VisLingInstruct tackles this by autonomously evaluating and optimizing instructional texts through In-Context Learning, improving the synergy between visual perception and linguistic expression in MMLMs. Alongside this instructional advancement, we have also optimized the visual feature extraction modules in MMLMs, further augment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07398","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/2402.07398/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":"2402.07398","created_at":"2026-07-05T08:34:47.324539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07398v3","created_at":"2026-07-05T08:34:47.324539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07398","created_at":"2026-07-05T08:34:47.324539+00:00"},{"alias_kind":"pith_short_12","alias_value":"XQYCD3ZNLJEU","created_at":"2026-07-05T08:34:47.324539+00:00"},{"alias_kind":"pith_short_16","alias_value":"XQYCD3ZNLJEUCWE2","created_at":"2026-07-05T08:34:47.324539+00:00"},{"alias_kind":"pith_short_8","alias_value":"XQYCD3ZN","created_at":"2026-07-05T08:34:47.324539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.05684","citing_title":"MM-FusionNet: Context-Aware Dynamic Fusion for Multi-modal Fake News Detection with Large Vision-Language Models","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XQYCD3ZNLJEUCWE2ZCP3BTEJWM","json":"https://pith.science/pith/XQYCD3ZNLJEUCWE2ZCP3BTEJWM.json","graph_json":"https://pith.science/api/pith-number/XQYCD3ZNLJEUCWE2ZCP3BTEJWM/graph.json","events_json":"https://pith.science/api/pith-number/XQYCD3ZNLJEUCWE2ZCP3BTEJWM/events.json","paper":"https://pith.science/paper/XQYCD3ZN"},"agent_actions":{"view_html":"https://pith.science/pith/XQYCD3ZNLJEUCWE2ZCP3BTEJWM","download_json":"https://pith.science/pith/XQYCD3ZNLJEUCWE2ZCP3BTEJWM.json","view_paper":"https://pith.science/paper/XQYCD3ZN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07398&json=true","fetch_graph":"https://pith.science/api/pith-number/XQYCD3ZNLJEUCWE2ZCP3BTEJWM/graph.json","fetch_events":"https://pith.science/api/pith-number/XQYCD3ZNLJEUCWE2ZCP3BTEJWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XQYCD3ZNLJEUCWE2ZCP3BTEJWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XQYCD3ZNLJEUCWE2ZCP3BTEJWM/action/storage_attestation","attest_author":"https://pith.science/pith/XQYCD3ZNLJEUCWE2ZCP3BTEJWM/action/author_attestation","sign_citation":"https://pith.science/pith/XQYCD3ZNLJEUCWE2ZCP3BTEJWM/action/citation_signature","submit_replication":"https://pith.science/pith/XQYCD3ZNLJEUCWE2ZCP3BTEJWM/action/replication_record"}},"created_at":"2026-07-05T08:34:47.324539+00:00","updated_at":"2026-07-05T08:34:47.324539+00:00"}