{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:D4EVPVXMZJZ4VXWU2WWGGDU3XT","short_pith_number":"pith:D4EVPVXM","schema_version":"1.0","canonical_sha256":"1f0957d6ecca73caded4d5ac630e9bbccadebb9122f4721d759932ade44f229d","source":{"kind":"arxiv","id":"2506.16406","version":1},"attestation_state":"computed","paper":{"title":"Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Damian Borth, Dongwen Tang, Kai Wang, Konstantin Sch\\\"urholt, Michael M. Bronstein, Mingjia Shi, Peihao Wang, Wangbo Zhao, Xuanlei Zhao, Yang You, Yuhao Zhou, Zekai Li, Zhangyang Wang, Zhiyuan Liang","submitted_at":"2025-06-19T15:38:21Z","abstract_excerpt":"Modern Parameter-Efficient Fine-Tuning (PEFT) methods such as low-rank adaptation (LoRA) reduce the cost of customizing large language models (LLMs), yet still require a separate optimization run for every downstream dataset. We introduce \\textbf{Drag-and-Drop LLMs (\\textit{DnD})}, a prompt-conditioned parameter generator that eliminates per-task training by mapping a handful of unlabeled task prompts directly to LoRA weight updates. A lightweight text encoder distills each prompt batch into condition embeddings, which are then transformed by a cascaded hyper-convolutional decoder into the ful"},"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":"2506.16406","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T15:38:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fde972ae3e52fe537ddc56e7de7c96082f25cab4f6dffcdaa013966cbcfa4ca1","abstract_canon_sha256":"fce0731e518cb54c4397f86b5da3cd1df47648a965cc46b75212a6622228dba2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:36.018386Z","signature_b64":"RUmn0bOeerr8DLE1mVsA91ZU/koQILubVZnXpZwpZDXJTDu9bH4JExQce9ujA5Rusknwaq5nGBhVmUHyUydiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f0957d6ecca73caded4d5ac630e9bbccadebb9122f4721d759932ade44f229d","last_reissued_at":"2026-07-05T11:24:36.017755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:36.017755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Damian Borth, Dongwen Tang, Kai Wang, Konstantin Sch\\\"urholt, Michael M. Bronstein, Mingjia Shi, Peihao Wang, Wangbo Zhao, Xuanlei Zhao, Yang You, Yuhao Zhou, Zekai Li, Zhangyang Wang, Zhiyuan Liang","submitted_at":"2025-06-19T15:38:21Z","abstract_excerpt":"Modern Parameter-Efficient Fine-Tuning (PEFT) methods such as low-rank adaptation (LoRA) reduce the cost of customizing large language models (LLMs), yet still require a separate optimization run for every downstream dataset. We introduce \\textbf{Drag-and-Drop LLMs (\\textit{DnD})}, a prompt-conditioned parameter generator that eliminates per-task training by mapping a handful of unlabeled task prompts directly to LoRA weight updates. A lightweight text encoder distills each prompt batch into condition embeddings, which are then transformed by a cascaded hyper-convolutional decoder into the ful"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16406","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/2506.16406/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":"2506.16406","created_at":"2026-07-05T11:24:36.017823+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.16406v1","created_at":"2026-07-05T11:24:36.017823+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16406","created_at":"2026-07-05T11:24:36.017823+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4EVPVXMZJZ4","created_at":"2026-07-05T11:24:36.017823+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4EVPVXMZJZ4VXWU","created_at":"2026-07-05T11:24:36.017823+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4EVPVXM","created_at":"2026-07-05T11:24:36.017823+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05300","citing_title":"Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07217","citing_title":"Robotic Policy Adaptation via Weight-Space Meta-Learning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30260","citing_title":"How LoRA Remembers? A Parametric Memory Law for LLM Finetuning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2505.13919","citing_title":"Generative Adaptation of Dynamics to Environmental Shifts via Weight-space Diffusion","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20189","citing_title":"SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18474","citing_title":"Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generation","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D4EVPVXMZJZ4VXWU2WWGGDU3XT","json":"https://pith.science/pith/D4EVPVXMZJZ4VXWU2WWGGDU3XT.json","graph_json":"https://pith.science/api/pith-number/D4EVPVXMZJZ4VXWU2WWGGDU3XT/graph.json","events_json":"https://pith.science/api/pith-number/D4EVPVXMZJZ4VXWU2WWGGDU3XT/events.json","paper":"https://pith.science/paper/D4EVPVXM"},"agent_actions":{"view_html":"https://pith.science/pith/D4EVPVXMZJZ4VXWU2WWGGDU3XT","download_json":"https://pith.science/pith/D4EVPVXMZJZ4VXWU2WWGGDU3XT.json","view_paper":"https://pith.science/paper/D4EVPVXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.16406&json=true","fetch_graph":"https://pith.science/api/pith-number/D4EVPVXMZJZ4VXWU2WWGGDU3XT/graph.json","fetch_events":"https://pith.science/api/pith-number/D4EVPVXMZJZ4VXWU2WWGGDU3XT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4EVPVXMZJZ4VXWU2WWGGDU3XT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4EVPVXMZJZ4VXWU2WWGGDU3XT/action/storage_attestation","attest_author":"https://pith.science/pith/D4EVPVXMZJZ4VXWU2WWGGDU3XT/action/author_attestation","sign_citation":"https://pith.science/pith/D4EVPVXMZJZ4VXWU2WWGGDU3XT/action/citation_signature","submit_replication":"https://pith.science/pith/D4EVPVXMZJZ4VXWU2WWGGDU3XT/action/replication_record"}},"created_at":"2026-07-05T11:24:36.017823+00:00","updated_at":"2026-07-05T11:24:36.017823+00:00"}