{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MENHCKIKZ25NBS7IR7YH4ZHC2S","short_pith_number":"pith:MENHCKIK","schema_version":"1.0","canonical_sha256":"611a71290acebad0cbe88ff07e64e2d49e16f451e78ed9dbbaaa5943c2a01418","source":{"kind":"arxiv","id":"2606.27527","version":1},"attestation_state":"computed","paper":{"title":"Large Language Model Teaches Visual Students: Cross-Modality Transfer of Fine-Grained Conceptual Knowledge","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Thomas Shih-Chao Liang, Yong Jae Lee, Zhuoran Yu","submitted_at":"2026-06-25T20:19:50Z","abstract_excerpt":"Large Language Models (LLMs) possess broad conceptual knowledge acquired through large-scale text pretraining, yet their potential to supervise models in other modalities remains underexplored. In this work, we propose LaViD--Language-to-Visual Knowledge Distillation--a simple and effective framework for transferring high-level semantic knowledge from a language-only teacher to a vision-only student model. Instead of relying on paired multimodal data, LaViD elicits conceptual signals from an LLM by prompting it to generate multiple-choice questions (MCQs) that probe semantic distinctions betwe"},"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":"2606.27527","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T20:19:50Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d8675572c86724ee9dbbb9f058f3b0d78bcc50ef58df6e7ed8538783d8c2d32c","abstract_canon_sha256":"e3cf1c968081d8b8117a14db4bd24df3af083ac790b804bf14d45031801a72c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T00:14:09.088594Z","signature_b64":"TeUeU2PvhIW0aORoyUnoNwX0vpoiJg9jOmzD2rA/XJtSDuK/QVRXxSMOfULKIHGQ3rj/yAVjkTGY6S+PvB9iDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"611a71290acebad0cbe88ff07e64e2d49e16f451e78ed9dbbaaa5943c2a01418","last_reissued_at":"2026-06-29T00:14:09.088115Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T00:14:09.088115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Model Teaches Visual Students: Cross-Modality Transfer of Fine-Grained Conceptual Knowledge","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Thomas Shih-Chao Liang, Yong Jae Lee, Zhuoran Yu","submitted_at":"2026-06-25T20:19:50Z","abstract_excerpt":"Large Language Models (LLMs) possess broad conceptual knowledge acquired through large-scale text pretraining, yet their potential to supervise models in other modalities remains underexplored. In this work, we propose LaViD--Language-to-Visual Knowledge Distillation--a simple and effective framework for transferring high-level semantic knowledge from a language-only teacher to a vision-only student model. Instead of relying on paired multimodal data, LaViD elicits conceptual signals from an LLM by prompting it to generate multiple-choice questions (MCQs) that probe semantic distinctions betwe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27527","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/2606.27527/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":"2606.27527","created_at":"2026-06-29T00:14:09.088171+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27527v1","created_at":"2026-06-29T00:14:09.088171+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27527","created_at":"2026-06-29T00:14:09.088171+00:00"},{"alias_kind":"pith_short_12","alias_value":"MENHCKIKZ25N","created_at":"2026-06-29T00:14:09.088171+00:00"},{"alias_kind":"pith_short_16","alias_value":"MENHCKIKZ25NBS7I","created_at":"2026-06-29T00:14:09.088171+00:00"},{"alias_kind":"pith_short_8","alias_value":"MENHCKIK","created_at":"2026-06-29T00:14:09.088171+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/MENHCKIKZ25NBS7IR7YH4ZHC2S","json":"https://pith.science/pith/MENHCKIKZ25NBS7IR7YH4ZHC2S.json","graph_json":"https://pith.science/api/pith-number/MENHCKIKZ25NBS7IR7YH4ZHC2S/graph.json","events_json":"https://pith.science/api/pith-number/MENHCKIKZ25NBS7IR7YH4ZHC2S/events.json","paper":"https://pith.science/paper/MENHCKIK"},"agent_actions":{"view_html":"https://pith.science/pith/MENHCKIKZ25NBS7IR7YH4ZHC2S","download_json":"https://pith.science/pith/MENHCKIKZ25NBS7IR7YH4ZHC2S.json","view_paper":"https://pith.science/paper/MENHCKIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27527&json=true","fetch_graph":"https://pith.science/api/pith-number/MENHCKIKZ25NBS7IR7YH4ZHC2S/graph.json","fetch_events":"https://pith.science/api/pith-number/MENHCKIKZ25NBS7IR7YH4ZHC2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MENHCKIKZ25NBS7IR7YH4ZHC2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MENHCKIKZ25NBS7IR7YH4ZHC2S/action/storage_attestation","attest_author":"https://pith.science/pith/MENHCKIKZ25NBS7IR7YH4ZHC2S/action/author_attestation","sign_citation":"https://pith.science/pith/MENHCKIKZ25NBS7IR7YH4ZHC2S/action/citation_signature","submit_replication":"https://pith.science/pith/MENHCKIKZ25NBS7IR7YH4ZHC2S/action/replication_record"}},"created_at":"2026-06-29T00:14:09.088171+00:00","updated_at":"2026-06-29T00:14:09.088171+00:00"}