{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:57DIOOZHQ5H75U5MV2QNBGHDZT","short_pith_number":"pith:57DIOOZH","schema_version":"1.0","canonical_sha256":"efc6873b27874ffed3acaea0d098e3cccea53afc330de5b43f2c037665f0eede","source":{"kind":"arxiv","id":"2311.08172","version":2},"attestation_state":"computed","paper":{"title":"Vision-Language Instruction Tuning: A Review and Analysis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.MM","authors_text":"Chen Li, Dian Li, Ying Shan, Yixiao Ge","submitted_at":"2023-11-14T14:02:32Z","abstract_excerpt":"Instruction tuning is a crucial supervised training phase in Large Language Models (LLMs), aiming to enhance the LLM's ability to generalize instruction execution and adapt to user preferences. With the increasing integration of multi-modal data into LLMs, there is growing interest in Vision-Language Instruction Tuning (VLIT), which presents more complex characteristics compared to pure text instruction tuning. In this paper, we systematically review the latest VLIT settings and corresponding datasets in multi-modal LLMs and provide insights into the intrinsic motivations behind their design. "},"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":"2311.08172","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.MM","submitted_at":"2023-11-14T14:02:32Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"13b422ba8496b8cff46b393bf3aaa677e96218ece8e2d7a7fd5971fdde64d083","abstract_canon_sha256":"b87ff86dbe637a688693e10564c6d8395a92f1daccfc9c20a7c26f910441d977"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:49.542807Z","signature_b64":"awn2OaldnvvS/xmgld9pTXdrjeGnBd3RaJScG+KRNbf5RONp0dWfcJVCiJLTqg6I+jEQsTKhzZ+RXZvEwNBEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efc6873b27874ffed3acaea0d098e3cccea53afc330de5b43f2c037665f0eede","last_reissued_at":"2026-07-05T07:16:49.542351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:49.542351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-Language Instruction Tuning: A Review and Analysis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.MM","authors_text":"Chen Li, Dian Li, Ying Shan, Yixiao Ge","submitted_at":"2023-11-14T14:02:32Z","abstract_excerpt":"Instruction tuning is a crucial supervised training phase in Large Language Models (LLMs), aiming to enhance the LLM's ability to generalize instruction execution and adapt to user preferences. With the increasing integration of multi-modal data into LLMs, there is growing interest in Vision-Language Instruction Tuning (VLIT), which presents more complex characteristics compared to pure text instruction tuning. In this paper, we systematically review the latest VLIT settings and corresponding datasets in multi-modal LLMs and provide insights into the intrinsic motivations behind their design. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08172","kind":"arxiv","version":2},"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/2311.08172/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":"2311.08172","created_at":"2026-07-05T07:16:49.542412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.08172v2","created_at":"2026-07-05T07:16:49.542412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08172","created_at":"2026-07-05T07:16:49.542412+00:00"},{"alias_kind":"pith_short_12","alias_value":"57DIOOZHQ5H7","created_at":"2026-07-05T07:16:49.542412+00:00"},{"alias_kind":"pith_short_16","alias_value":"57DIOOZHQ5H75U5M","created_at":"2026-07-05T07:16:49.542412+00:00"},{"alias_kind":"pith_short_8","alias_value":"57DIOOZH","created_at":"2026-07-05T07:16:49.542412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17030","citing_title":"Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation","ref_index":172,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20914","citing_title":"RISE: Reliable Improvement in Self-Evolving Vision-Language Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20914","citing_title":"RISE: Reliable Improvement in Self-Evolving Vision-Language Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2404.14396","citing_title":"SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/57DIOOZHQ5H75U5MV2QNBGHDZT","json":"https://pith.science/pith/57DIOOZHQ5H75U5MV2QNBGHDZT.json","graph_json":"https://pith.science/api/pith-number/57DIOOZHQ5H75U5MV2QNBGHDZT/graph.json","events_json":"https://pith.science/api/pith-number/57DIOOZHQ5H75U5MV2QNBGHDZT/events.json","paper":"https://pith.science/paper/57DIOOZH"},"agent_actions":{"view_html":"https://pith.science/pith/57DIOOZHQ5H75U5MV2QNBGHDZT","download_json":"https://pith.science/pith/57DIOOZHQ5H75U5MV2QNBGHDZT.json","view_paper":"https://pith.science/paper/57DIOOZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.08172&json=true","fetch_graph":"https://pith.science/api/pith-number/57DIOOZHQ5H75U5MV2QNBGHDZT/graph.json","fetch_events":"https://pith.science/api/pith-number/57DIOOZHQ5H75U5MV2QNBGHDZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57DIOOZHQ5H75U5MV2QNBGHDZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57DIOOZHQ5H75U5MV2QNBGHDZT/action/storage_attestation","attest_author":"https://pith.science/pith/57DIOOZHQ5H75U5MV2QNBGHDZT/action/author_attestation","sign_citation":"https://pith.science/pith/57DIOOZHQ5H75U5MV2QNBGHDZT/action/citation_signature","submit_replication":"https://pith.science/pith/57DIOOZHQ5H75U5MV2QNBGHDZT/action/replication_record"}},"created_at":"2026-07-05T07:16:49.542412+00:00","updated_at":"2026-07-05T07:16:49.542412+00:00"}