{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TBD5KIMFLFDX6XGO3QK4ZYUVBM","short_pith_number":"pith:TBD5KIMF","schema_version":"1.0","canonical_sha256":"9847d5218559477f5ccedc15cce2950b29dbe3358a2493337014bd9721686a9c","source":{"kind":"arxiv","id":"2412.02220","version":1},"attestation_state":"computed","paper":{"title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Dacheng Tao, Li Shen, Yongxian Wei, Zixuan Hu","submitted_at":"2024-12-03T07:25:30Z","abstract_excerpt":"Large Language Models (LLMs) such as ChatGPT demonstrate strong few-shot adaptability without requiring fine-tuning, positioning them ideal for data-limited and real-time applications. However, this adaptability has not yet been replicated in current Visual Foundation Models (VFMs), which require explicit fine-tuning with sufficient tuning data. Besides, the pretraining-finetuning paradigm has led to the surge of numerous task-specific modular components, such as Low-Rank Adaptation (LoRA). For the first time, we explore the potential of reusing diverse pre-tuned LoRAs without accessing their "},"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":"2412.02220","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T07:25:30Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"747ed9e0ed85067a467695069230e8cd19e18c084d2ecfb7ca2d184df196eba0","abstract_canon_sha256":"89e513fe1d47004c18701eac89f4ff6c79d5463bbae69d7459a20bfe89dd94fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:46.315228Z","signature_b64":"JNFWQbBOwWxzFkvYHcbem0XUv9TlQhTrDX+/EAushwVCKObcswcY7ne91GZF+ktCbU9y3SeHSH3NvC0iWyJNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9847d5218559477f5ccedc15cce2950b29dbe3358a2493337014bd9721686a9c","last_reissued_at":"2026-07-05T09:43:46.314845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:46.314845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Dacheng Tao, Li Shen, Yongxian Wei, Zixuan Hu","submitted_at":"2024-12-03T07:25:30Z","abstract_excerpt":"Large Language Models (LLMs) such as ChatGPT demonstrate strong few-shot adaptability without requiring fine-tuning, positioning them ideal for data-limited and real-time applications. However, this adaptability has not yet been replicated in current Visual Foundation Models (VFMs), which require explicit fine-tuning with sufficient tuning data. Besides, the pretraining-finetuning paradigm has led to the surge of numerous task-specific modular components, such as Low-Rank Adaptation (LoRA). For the first time, we explore the potential of reusing diverse pre-tuned LoRAs without accessing their "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02220","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/2412.02220/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":"2412.02220","created_at":"2026-07-05T09:43:46.314906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02220v1","created_at":"2026-07-05T09:43:46.314906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02220","created_at":"2026-07-05T09:43:46.314906+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBD5KIMFLFDX","created_at":"2026-07-05T09:43:46.314906+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBD5KIMFLFDX6XGO","created_at":"2026-07-05T09:43:46.314906+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBD5KIMF","created_at":"2026-07-05T09:43:46.314906+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/TBD5KIMFLFDX6XGO3QK4ZYUVBM","json":"https://pith.science/pith/TBD5KIMFLFDX6XGO3QK4ZYUVBM.json","graph_json":"https://pith.science/api/pith-number/TBD5KIMFLFDX6XGO3QK4ZYUVBM/graph.json","events_json":"https://pith.science/api/pith-number/TBD5KIMFLFDX6XGO3QK4ZYUVBM/events.json","paper":"https://pith.science/paper/TBD5KIMF"},"agent_actions":{"view_html":"https://pith.science/pith/TBD5KIMFLFDX6XGO3QK4ZYUVBM","download_json":"https://pith.science/pith/TBD5KIMFLFDX6XGO3QK4ZYUVBM.json","view_paper":"https://pith.science/paper/TBD5KIMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02220&json=true","fetch_graph":"https://pith.science/api/pith-number/TBD5KIMFLFDX6XGO3QK4ZYUVBM/graph.json","fetch_events":"https://pith.science/api/pith-number/TBD5KIMFLFDX6XGO3QK4ZYUVBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBD5KIMFLFDX6XGO3QK4ZYUVBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBD5KIMFLFDX6XGO3QK4ZYUVBM/action/storage_attestation","attest_author":"https://pith.science/pith/TBD5KIMFLFDX6XGO3QK4ZYUVBM/action/author_attestation","sign_citation":"https://pith.science/pith/TBD5KIMFLFDX6XGO3QK4ZYUVBM/action/citation_signature","submit_replication":"https://pith.science/pith/TBD5KIMFLFDX6XGO3QK4ZYUVBM/action/replication_record"}},"created_at":"2026-07-05T09:43:46.314906+00:00","updated_at":"2026-07-05T09:43:46.314906+00:00"}