{"as_of":"2026-08-13T04:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:547fdf0eccf65169c38609f588161bbf2464b05a6dcc604a62b72dbbbe5b7fea","coverage":[{"denominator":75,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":75,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T23:49:02.568731Z","state":"measured"},{"denominator":75,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":75,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.02220/citation-record","integrity":"/paper/2412.02220/integrity","json":"/paper/2412.02220/citation-record.json","paper":"/paper/2412.02220"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:04.126517Z","title":"Meta-adapters: Parameter ef- ficient few-shot fine-tuning through meta-learning","venue":null,"work_id":"641f83c2-98b5-4a1f-997f-59bf92de2e5e","year":2022},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.127279Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:2349db4aac05744ce2901a0110ac77602c3b9b5ffa16eeec5be98aea41e6208f","observation_id":"0398907c-d6d2-47b2-a837-b297d1ec5d04","resolution":{"observed_at":"2026-08-11T23:49:04.131906Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.08136","last_updated":"2019-07-24T14:43:31Z","snapshot_observed_at":"2026-08-10T12:54:21.108689Z","submitted_at":"2018-05-21T15:44:51Z","title":"Meta-learning with differentiable closed-form solvers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.08136","snapshot_observed_at":"2026-08-11T23:49:02.134452Z","title":"Meta-learning with differentiable closed-form solvers","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.134452Z"},"links":{"cited_paper":"/paper/1805.08136","citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:db5f73ba0d54c4d2fb9370f632ace167b415a135049e5380c9d0b8052d74538f","observation_id":"6d44be06-e06a-4cf7-8e62-654c471a8646","resolution":{"observed_at":"2026-08-11T23:49:02.134452Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:02.142979Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.142979Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:ed4a0c7d4a20a8e07ff9880dbc3432c875bde5bfcb01d7e00f9809a0c2fd9982","observation_id":"2773f58c-774f-4cf9-913a-1b49a686fb92","resolution":{"observed_at":"2026-08-11T23:49:02.142979Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.10544","last_updated":"2020-08-25T15:45:55Z","snapshot_observed_at":"2026-07-06T09:22:14.248788Z","submitted_at":"2020-05-21T09:55:26Z","title":"Cross-Domain Few-Shot Learning with Meta Fine-Tuning","version":4},"cited_work":{"arxiv_id":"2005.10544","doi":null,"metadata_source":"pith","pith_arxiv_id":"2005.10544","snapshot_observed_at":"2026-08-11T23:49:03.035153Z","title":"Cross-Domain Few-Shot Learning with Meta Fine-Tuning","venue":"cs.CV","work_id":"243937c9-7f96-409d-817a-a3affcdc71b6","year":2020},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.149775Z"},"links":{"cited_paper":"/paper/2005.10544","citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:148a1cd7b0b742bed12579649bf10b487888a1134e8751e99ae409d2f930ca50","observation_id":"759da982-b367-4826-b978-d2bec3875ee3","resolution":{"observed_at":"2026-08-11T23:49:03.042628Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.16160","last_updated":"2024-01-30T15:44:58Z","snapshot_observed_at":"2026-07-06T17:21:51.054477Z","submitted_at":"2024-01-29T13:48:36Z","title":"LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.16160","snapshot_observed_at":"2026-08-11T23:49:02.155342Z","title":"Llava-mole: Sparse mixture of lora experts for mitigating data con- flicts in instruction finetuning mllms","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.155342Z"},"links":{"cited_paper":"/paper/2401.16160","citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:0a2f539a0a4ca982085cd1bc789e74847e5495300bb70c2791a9e6f6a05d346e","observation_id":"6164bfe4-553e-4a0e-954a-1ee7e3d32d9a","resolution":{"observed_at":"2026-08-11T23:49:02.155342Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:04.090156Z","title":"Meta-learning via language model in-context tuning","venue":null,"work_id":"0d08f6c1-1153-4651-a3a4-6a281da630d0","year":2022},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.161410Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:6ba5bfc3d254dd0584d907c1c53d595bdb3b995e1d0e4b5f09d65a77888bedb1","observation_id":"98f0a992-d845-4112-bafd-bc6b50459adb","resolution":{"observed_at":"2026-08-11T23:49:04.096899Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.11416","last_updated":"2022-12-06T21:39:48Z","snapshot_observed_at":"2026-07-06T14:08:18.855958Z","submitted_at":"2022-10-20T16:58:32Z","title":"Scaling Instruction-Finetuned Language Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.11416","snapshot_observed_at":"2026-08-11T23:49:02.167253Z","title":"Scaling instruction-finetuned language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.167253Z"},"links":{"cited_paper":"/paper/2210.11416","citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:a6bc98f2221c059904a9766db71a3c6131269268af4140a5bc8950d678568fa0","observation_id":"9c0105b8-6747-40e2-9375-8cb96af366c5","resolution":{"observed_at":"2026-08-11T23:49:02.167253Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.10559","last_updated":"2023-05-15T11:45:12Z","snapshot_observed_at":"2026-08-09T08:03:27.441735Z","submitted_at":"2022-12-20T18:58:48Z","title":"Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.10559","snapshot_observed_at":"2026-08-11T23:49:02.172820Z","title":"Why can gpt learn in-context? language models implicitly perform gradient descent as meta-optimizers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.172820Z"},"links":{"cited_paper":"/paper/2212.10559","citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:e0ba4ecccfe94cb6383a77844d04656771ae2f48ed1abbb01375d33139c0ce87","observation_id":"6302d483-60fa-4130-8c41-ea088a873d2a","resolution":{"observed_at":"2026-08-11T23:49:02.172820Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.00234","last_updated":"2024-10-05T11:47:02Z","snapshot_observed_at":"2026-07-06T14:36:25.690733Z","submitted_at":"2022-12-31T15:57:09Z","title":"A Survey on In-context Learning","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.00234","snapshot_observed_at":"2026-08-11T23:49:02.178226Z","title":"A survey on in-context learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.178226Z"},"links":{"cited_paper":"/paper/2301.00234","citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:de6848870b609f9e8d80634d122250c7e4564e6eb9ebdf5a5c8342b5a1a88b4a","observation_id":"55d85c64-64ef-4bd7-bef9-1f6995a75538","resolution":{"observed_at":"2026-08-11T23:49:02.178226Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.08584","last_updated":"2021-05-18T15:13:00Z","snapshot_observed_at":"2026-08-08T13:22:47.133749Z","submitted_at":"2021-05-18T15:13:00Z","title":"Contrastive Model Inversion for Data-Free Knowledge Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.08584","snapshot_observed_at":"2026-08-11T23:49:02.184624Z","title":"Contrastive model inver- sion for data-free knowledge distillation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.184624Z"},"links":{"cited_paper":"/paper/2105.08584","citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:34097f228daf7236be14b4e6796c6bd69e499ac19c920f8454e34dfa4ce9c0fc","observation_id":"4397f209-fc49-4de8-9e79-5a580d1374fa","resolution":{"observed_at":"2026-08-11T23:49:02.184624Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:04.068678Z","title":"Up to 100x faster data- free knowledge distillation","venue":null,"work_id":"343809a3-ed64-4b60-af26-992a2493804f","year":2022},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.190260Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:1598f391ea0c5c7e446d22461e06584836f54535d12ed52822cb88afd4c658cd","observation_id":"63bccb93-515f-471f-a58e-0cb33bd1cbfb","resolution":{"observed_at":"2026-08-11T23:49:04.075600Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.10971","last_updated":"2024-03-25T23:14:28Z","snapshot_observed_at":"2026-08-06T03:56:52.792686Z","submitted_at":"2023-10-17T03:35:27Z","title":"Context-Aware Meta-Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.10971","snapshot_observed_at":"2026-08-11T23:49:02.195611Z","title":"Context-aware meta-learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.195611Z"},"links":{"cited_paper":"/paper/2310.10971","citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:81fab4e28d90014e2e30cbfe1e8caa10dd9d81534ee7689fa8573dcf2a38761e","observation_id":"5708a13d-bfd0-4324-b240-d6de891addbe","resolution":{"observed_at":"2026-08-11T23:49:02.195611Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:04.042164Z","title":"Model- agnostic meta-learning for fast adaptation of deep networks","venue":null,"work_id":"14c8f978-8d6b-4570-bb77-946499b27b5f","year":2017},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.203090Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:c03c9a90bfeabee738a950bdf8f63209fa92ed21d6eb268057c9afc63d7ece4d","observation_id":"9576cb3c-48e7-493d-b7a8-65e8812bf5b1","resolution":{"observed_at":"2026-08-11T23:49:04.048319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:04.022075Z","title":"Styleadv: Meta style adversarial training for cross-domain few-shot learning","venue":null,"work_id":"ea5e4327-3124-4264-9e79-d83b49ec2186","year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.208766Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:8228f561bc676bf893ae749df744d2869f0cc417996cc3a4d87ecdca7303238f","observation_id":"be3b4612-f74a-4243-ac22-231e943c781b","resolution":{"observed_at":"2026-08-11T23:49:04.028401Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:04.003320Z","title":"On the effectiveness of parameter-efficient fine-tuning","venue":null,"work_id":"43da96b1-b670-4b53-93db-9138d22a1d7e","year":null},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.213937Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:84ee923ffdff9a89dfe3e16b37e347cd1a3d240f4dab90525b348d1ee14254b4","observation_id":"e0814a38-e52c-4204-ba05-994e92b0de07","resolution":{"observed_at":"2026-08-11T23:49:04.008522Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:02.219408Z","title":"Clip-adapter: Better vision-language models with feature adapters","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.219408Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:d0e1434501d63b7a9bf1c4eedf27d56681b223770b4979ba53c41df7e3638b6c","observation_id":"b20f672c-0898-4b0f-8207-528475496e7d","resolution":{"observed_at":"2026-08-11T23:49:02.219408Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.965368Z","title":"Know where you’re going: Meta-learning for parameter-efficient fine-tuning","venue":null,"work_id":"43698f74-28f6-4ab6-ac63-e479ed692811","year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.226066Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:5ec2f9f9f596b1171f8043b97f867e80ead771bc79d0c66312de61efba025fb4","observation_id":"b2a36af5-b307-45bf-aba0-ef00fd7bb434","resolution":{"observed_at":"2026-08-11T23:49:03.972440Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.12379","last_updated":"2024-07-04T02:55:57Z","snapshot_observed_at":"2026-07-06T17:05:27.005904Z","submitted_at":"2023-12-19T18:11:19Z","title":"Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.12379","snapshot_observed_at":"2026-08-11T23:49:02.231977Z","title":"Mixture of cluster-conditional lora experts for vision-language instruction tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.231977Z"},"links":{"cited_paper":"/paper/2312.12379","citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:5f65e315faa1171e3794da7d086d2a2fe9d76ba5ffa6c6b2354c37d9d7dc442b","observation_id":"3df9cc27-a4e3-4023-aa38-fa02beff9771","resolution":{"observed_at":"2026-08-11T23:49:02.231977Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.943160Z","title":"A broader study of cross-domain few-shot learning","venue":null,"work_id":"b8ac7810-d65c-40a6-9930-5bfd9a57978c","year":2020},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.239064Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:97a045ab3e86cd3ce1ed2ffcfb242ae3044a1b85b5a1aa82e47e5f93a8cbfd71","observation_id":"7376e1aa-cfe5-42e4-9844-59777a4178c4","resolution":{"observed_at":"2026-08-11T23:49:03.950577Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.920938Z","title":"Gradvit: 9 Gradient inversion of vision transformers","venue":null,"work_id":"11148183-aec7-4acc-b129-1fc8163334f0","year":2022},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.244981Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:651b9b5595c7d532e96cd745c693261e715b6492b85c203a991c5a9cf0ba220d","observation_id":"09762856-406f-42fc-9ed0-c29637a2a080","resolution":{"observed_at":"2026-08-11T23:49:03.927687Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.04366","last_updated":"2022-02-02T16:39:23Z","snapshot_observed_at":"2026-08-09T04:45:04.547249Z","submitted_at":"2021-10-08T20:22:26Z","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.04366","snapshot_observed_at":"2026-08-11T23:49:02.250584Z","title":"Towards a unified view of parameter-efficient transfer learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.250584Z"},"links":{"cited_paper":"/paper/2110.04366","citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:c722bbd088b10a7bc71626dd310ff7c3eb98c1ac4e5ad48c947e6150c2a353a4","observation_id":"8bb711c1-9f0f-4ea8-8aa8-ee0f09296f97","resolution":{"observed_at":"2026-08-11T23:49:02.250584Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.898511Z","title":"Towards a unified view of parameter-efficient transfer learning","venue":null,"work_id":"707ea0fd-8d88-4262-bf47-36780f997dce","year":2022},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.258909Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:15449c875619b7b2f0b4b45860e2d42218a8274e74f6135fe0b754a9aa0a1c5d","observation_id":"acd18b08-8764-46a5-8a69-7c68abb8d055","resolution":{"observed_at":"2026-08-11T23:49:03.905735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.875163Z","title":"Revisiting data-free knowledge distilla- tion with poisoned teachers","venue":null,"work_id":"641c3c42-2049-48bf-bfcf-3ab594f26f97","year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.264946Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:820409f2d44d4c08e4cef4d8578d9144e87d108aba048c52227a1f67c4dbcac2","observation_id":"96f52803-948f-47de-8db4-c5c112cbd286","resolution":{"observed_at":"2026-08-11T23:49:03.881719Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.855580Z","title":"Meta- learning the difference: preparing large language models for efficient adaptation","venue":null,"work_id":"658cf7b3-94a5-4744-8990-771e787a51d7","year":2022},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.275105Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:bd1b85c023ef2fc63eafe136d533d58fe493acf69043dd5c921565570d673b31","observation_id":"afa819e1-16ab-484d-97a8-9495e1172286","resolution":{"observed_at":"2026-08-11T23:49:03.862353Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:02.280736Z","title":"Parameter-efficient transfer learning for nlp","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.280736Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:5c776c29434ee2248c0664410c41ffac7dd0d5e5cc7148bfe2e0444bbb0940ab","observation_id":"43933b22-cd7b-44c2-ad0f-780c6454d2ae","resolution":{"observed_at":"2026-08-11T23:49:02.280736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-11T08:20:29.798517Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-11T23:49:02.286143Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.286143Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:736c2bbfdaeb094ca90ec053b50c84e121c701896a61f77f3482d2ff44612ce0","observation_id":"0fdfb6b8-2834-4cfa-89ad-e0a1858fcac6","resolution":{"observed_at":"2026-08-11T23:49:02.286143Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.821814Z","title":"Pushing the limits of simple pipelines for few-shot learning: External data and fine-tuning make a difference","venue":null,"work_id":"b00a2610-fcef-404c-9d3c-473bcd5e2d9b","year":2022},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.291901Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:50ed04e601398047abce790c76bb4f17dca3033a1a4e0ea168dcfce7d6aad705","observation_id":"66314701-0626-40e1-a278-d60b7440024f","resolution":{"observed_at":"2026-08-11T23:49:03.828602Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.802276Z","title":"Sparse model inversion: Ef- ficient inversion of vision transformers for data-free appli- cations","venue":null,"work_id":"6706e15c-55e9-4bbd-a166-822aa9e8f23c","year":null},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.297383Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:a1d6a81c3ea4fe6509b9c7a79616a763b65c777901e98df14eb029b29dc841dc","observation_id":"6c525abc-d9e1-4087-a956-b32cb615b343","resolution":{"observed_at":"2026-08-11T23:49:03.808035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.784279Z","title":"Architecture, dataset and model- scale agnostic data-free meta-learning","venue":null,"work_id":"9279a9f3-d400-46e9-97ac-fef0e5004311","year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.303216Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:07003ab21e44a1714e7ad8bbd3c977a107ce136c7316ca6dcaa45e7c5950bcc7","observation_id":"f48bd6a3-6be4-4a1a-adcc-8369362582ab","resolution":{"observed_at":"2026-08-11T23:49:03.790863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.18413","last_updated":"2025-02-15T05:56:37Z","snapshot_observed_at":"2026-07-06T15:34:59.457879Z","submitted_at":"2023-05-28T18:00:12Z","title":"Learning to Learn from APIs: Black-Box Data-Free Meta-Learning","version":3},"cited_work":{"arxiv_id":"2305.18413","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.18413","snapshot_observed_at":"2026-08-11T23:49:02.804617Z","title":"Learning to Learn from APIs: Black-Box Data-Free Meta-Learning","venue":"cs.LG","work_id":"0a6dfad9-8381-4952-82ae-e25ebe2ec2d1","year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.308233Z"},"links":{"cited_paper":"/paper/2305.18413","citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:d77768204577a5efd3eb28e2715ad79293ae2d1049b04c782feb65f9ef1991d7","observation_id":"e5538d31-8485-4076-8270-909a6a52e945","resolution":{"observed_at":"2026-08-11T23:49:02.811308Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-11T23:49:02.313137Z","title":"Lorahub: Efficient cross-task gen- eralization via dynamic lora composition","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.313137Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:d9a03f3fd164c900ab9e095bc3b8de695af8908f5c8ded44b6ac430900b64ef1","observation_id":"24e5e0b6-0edf-47bb-a3c8-f0b900d38ef1","resolution":{"observed_at":"2026-08-11T23:49:02.313137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.766828Z","title":"Diversity-aware meta visual prompting","venue":null,"work_id":"929538db-e2be-4943-b3df-2cf15d2c6260","year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.317993Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:e8902706fb97b22f258da3df962477ef22c65fb51034a10719ef617b8912dcd9","observation_id":"67e4d478-98e5-41d8-aa77-99000b29bdc0","resolution":{"observed_at":"2026-08-11T23:49:03.772301Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.12017","last_updated":"2023-01-30T05:25:59Z","snapshot_observed_at":"2026-08-02T23:44:31.455796Z","submitted_at":"2022-12-22T19:56:09Z","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.12017","snapshot_observed_at":"2026-08-11T23:49:02.323710Z","title":"Opt-iml: Scaling language model instruction meta learning through the lens of generalization","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.323710Z"},"links":{"cited_paper":"/paper/2212.12017","citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:a3531f9db400137cb4cc9e8040beb0f18383b68da668cf61aeba763f2710b819","observation_id":"1267bdaa-20b1-4db1-8fa0-010abb1b5c26","resolution":{"observed_at":"2026-08-11T23:49:02.323710Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.00690","last_updated":"2023-03-01T17:38:03Z","snapshot_observed_at":"2026-07-06T14:57:28.489012Z","submitted_at":"2023-03-01T17:38:03Z","title":"Rethinking Efficient Tuning Methods from a Unified Perspective","version":1},"cited_work":{"arxiv_id":"2303.00690","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.00690","snapshot_observed_at":"2026-08-11T23:49:02.728136Z","title":"Rethinking Efficient Tuning Methods from a Unified Perspective","venue":"cs.CV","work_id":"059c9662-bbae-4820-956f-1fc72e8f6316","year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.329299Z"},"links":{"cited_paper":"/paper/2303.00690","citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:e41e3d5e49a5f98cfa5d485bd59a060d85c9c267b35d4e26e9caf5699519c53a","observation_id":"efad1bf9-512b-43ac-8b9e-fd5108628ea6","resolution":{"observed_at":"2026-08-11T23:49:02.733698Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.747322Z","title":"All tokens matter: Token labeling for training better vision transform- ers","venue":null,"work_id":"e9291398-d511-48ba-a2dd-489ca77cfe34","year":2021},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.335305Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:f5a26e1944a1dc8939402898fafb4690c84558fc8dfa6337c762cac88e21af4a","observation_id":"6b9c6ca0-ad0e-4ab6-9fb9-66b63f48d5a8","resolution":{"observed_at":"2026-08-11T23:49:03.753681Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.729368Z","title":"Adaptive gradient-based meta-learning methods.Ad- vances in Neural Information Processing Systems, 32, 2019","venue":null,"work_id":"14205ee7-ea8e-42c5-843e-a5b59ca1bac9","year":2019},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.341780Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:ebf475ab3ba8595ba8b7ff0fe5bf2241c6370cf083552fc165b90d2d39d4a5e6","observation_id":"911b7ce2-6f46-481b-a298-bacb50eb329e","resolution":{"observed_at":"2026-08-11T23:49:03.734959Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.709992Z","title":"Token fusion: Bridging the gap between token pruning and token merging","venue":null,"work_id":"d5814613-a3db-45be-9582-d0f507851efb","year":2024},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.347824Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:7507b2d70557e1c4fe8026ba15a710cbb000d0272b7fff9857d498294e14a2a9","observation_id":"8e67df79-a96d-4d35-a080-8a84b58376eb","resolution":{"observed_at":"2026-08-11T23:49:03.715201Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.10054","last_updated":"2022-02-21T09:03:34Z","snapshot_observed_at":"2026-08-11T01:24:45.524652Z","submitted_at":"2022-02-21T09:03:34Z","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.10054","snapshot_observed_at":"2026-08-11T23:49:02.354758Z","title":"Fine-tuning can distort pretrained fea- tures and underperform out-of-distribution","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.354758Z"},"links":{"cited_paper":"/paper/2202.10054","citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:654d71b29fd355431fa756ef119bc55fd5f9f87c81052f38d18680d45bd71753","observation_id":"000d9fc0-8c14-4581-93b2-57792137d3a6","resolution":{"observed_at":"2026-08-11T23:49:02.354758Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.692081Z","title":"Surgical fine- tuning improves adaptation to distribution shifts","venue":null,"work_id":"67621588-298e-41d6-81c2-a287ec793089","year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.362440Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:09186fba93fb6fbe1445d7b0b137e8eba82436d1dfa3b6a24e4647e150807397","observation_id":"b4ff5f66-6d52-4bb4-9a2f-7cffd3c661f9","resolution":{"observed_at":"2026-08-11T23:49:03.697646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.675187Z","title":"Patch similarity aware data-free quantization for vision transformers","venue":null,"work_id":"378a0411-9782-4b63-ab90-03805eb98225","year":2022},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.368615Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:c689377a1e35165460e96b2569e18ef88384af7136a4cb48bf6f0d770a9f07bb","observation_id":"92fb4fdd-4403-439c-9dcf-7e3a1cdf0fff","resolution":{"observed_at":"2026-08-11T23:49:03.680222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.657657Z","title":"Psaq-vit v2: Toward accurate and general data-free quanti- zation for vision transformers","venue":null,"work_id":"55df09b0-0218-44a4-bd62-ba426440ad5f","year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.373825Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:1bacc0e89459f578bac709bed8ef2160ff7de5f490f9b2cb9903a036cea51e79","observation_id":"cbe51bc8-866c-48a9-86a5-0bae69b3b300","resolution":{"observed_at":"2026-08-11T23:49:03.663624Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.05963","last_updated":"2024-10-08T12:15:08Z","snapshot_observed_at":"2026-08-12T22:28:14.766739Z","submitted_at":"2024-10-08T12:15:08Z","title":"Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.05963","snapshot_observed_at":"2026-08-11T23:49:02.379022Z","title":"Training-free open-ended object detection and segmentation via attention as prompts","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.379022Z"},"links":{"cited_paper":"/paper/2410.05963","citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:73e71db9b013245c4b5038d5c43c2607b02ddded74ff5a9483f0fe116351b4fd","observation_id":"6740e6a6-3d75-4691-86ac-3f1fdfbe0eca","resolution":{"observed_at":"2026-08-11T23:49:02.379022Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.637897Z","title":"Few- shot parameter-efficient fine-tuning is better and cheaper than in-context learning","venue":null,"work_id":"d9330fa9-2639-432b-94d6-f9536b8bc21f","year":1950},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.384494Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:f63c5afdf5718597313aa386fd2279860044c1c1201216e06994a0e26381b0ad","observation_id":"1f8a181a-60c6-49a4-9f42-bea66e05abb9","resolution":{"observed_at":"2026-08-11T23:49:03.645142Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.616643Z","title":"Small scale data-free knowledge distillation","venue":null,"work_id":"5891ffc0-b8a1-4e72-9aa5-4513f3dd0eee","year":2024},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.389573Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:e5c46eb1c4e907623b9c806822b05e6b6af864fca7a7f50bc28f5cb0cea7f4be","observation_id":"4782d2d7-16ee-4f89-a6d5-b0404f8473c0","resolution":{"observed_at":"2026-08-11T23:49:03.623743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.591740Z","title":"Matcher: Segment anything with one shot using all-purpose feature matching","venue":null,"work_id":"19fdb3ad-1053-48ee-b8ee-f0ce29ec43b8","year":2024},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.394693Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:93de418fbe6f215ae782b3ebe5718906339b76e741d1291adc54cec891594b58","observation_id":"848cac0e-3ddc-4fb2-9e94-703102b2f999","resolution":{"observed_at":"2026-08-11T23:49:03.598581Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.571080Z","title":"DFRD: Data-free robustness distillation 10 for heterogeneous federated learning","venue":null,"work_id":"801e9da8-7eea-40db-a8eb-a9017a61c64b","year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.400713Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:9728d187ce39ce09f5e399002dc3ca27daa5ef98323e4828cbbefdd5415ac9d3","observation_id":"f2a9e153-e96f-4920-a3a1-a7a2859a8ccb","resolution":{"observed_at":"2026-08-11T23:49:03.578020Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.541955Z","title":"MetaICL: Learning to learn in context","venue":null,"work_id":"8a2d93af-f2dc-4e34-a613-04d634f94dd2","year":2022},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.406113Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:83837c2e55838f1e139e3e4520fe38ffac5966a69fa3dc8a0b0a5dc8c5b8127b","observation_id":"6a1ced4e-8f0b-4104-a2f6-673b79bb86a3","resolution":{"observed_at":"2026-08-11T23:49:03.548306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.520022Z","title":"Meta learning to bridge vision and language models for mul- timodal few-shot learning","venue":null,"work_id":"506def5b-859a-4536-b3f2-8f82e1129f26","year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.411119Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:164dcdf43c7263149fb3296d329e6f8339c7dc091787506a78ddd1cc191dca61","observation_id":"9644603e-d628-4d48-bc8d-df1f2fa2b869","resolution":{"observed_at":"2026-08-11T23:49:03.526604Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.02999","last_updated":"2018-10-22T16:11:14Z","snapshot_observed_at":"2026-08-05T12:53:31.632675Z","submitted_at":"2018-03-08T08:29:38Z","title":"On First-Order Meta-Learning Algorithms","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.02999","snapshot_observed_at":"2026-08-11T23:49:02.416026Z","title":"On first-order meta-learning algorithms","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.416026Z"},"links":{"cited_paper":"/paper/1803.02999","citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:56e0a087a2f3937814fec61c9712244c1ce17c287170fc2bc04ce09b3cc7e76e","observation_id":"fbdb9dc0-4022-4722-9d0d-45ae88edbebb","resolution":{"observed_at":"2026-08-11T23:49:02.416026Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:02.421377Z","title":"Automated flower classification over a large number of classes","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.421377Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:6478ffe9c4954bdd79199aa1f30071b3b3274e810d7e0e9f50c65609caaf41d1","observation_id":"2fd652f5-1824-4e59-99e2-37a95c63cc4f","resolution":{"observed_at":"2026-08-11T23:49:02.421377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:02.426404Z","title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.426404Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:e3bebaa44db5827b048909c99985231d8ed6bd9b15cc9ff0e3457ddd372450b3","observation_id":"ab31a570-5dcb-4296-bb01-b310e905a47d","resolution":{"observed_at":"2026-08-11T23:49:02.426404Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.478928Z","title":"Data-free knowledge distillation for fine-grained visual cat- egorization","venue":null,"work_id":"0a7eb193-5fc7-4b32-be7a-2be9f96731b7","year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.431781Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:a4ad5adb641234cd7cfb84ef443ee28821a343036c1f241253232a7439d75262","observation_id":"4117e486-ab06-4127-984c-14d44cb9c82c","resolution":{"observed_at":"2026-08-11T23:49:03.484986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.461636Z","title":"Prototypical networks for few-shot learning","venue":null,"work_id":"107e7b21-2d47-4585-abb9-a22fde15f999","year":2017},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.436745Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:fb461ac2948c8c89af52091d12200ee57af4930a783e0fbacb0d1b7bbd93fa02","observation_id":"812c7cdc-4a7d-41c4-91f0-8ebbdf5eb21e","resolution":{"observed_at":"2026-08-11T23:49:03.467187Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.443574Z","title":"Meta-transfer learning for few-shot learning","venue":null,"work_id":"26aaab4f-d2ff-4711-9d1e-01e385229b9e","year":2019},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.442097Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:83a74a18909af76a6d82a5108f36c7eecf726f0c8bfffa50763068e9d1c619b2","observation_id":"e7595bca-dab0-4482-8153-dc3c2735b9fb","resolution":{"observed_at":"2026-08-11T23:49:03.449516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.422657Z","title":"Training data-efficient image transformers & distillation through at- tention","venue":null,"work_id":"f3c62cb7-f50c-4152-9114-85012c4cba31","year":2021},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.447985Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:d0002352bfe2d8e4df8db0fa56a714ee9053e8a872bd38885eefc3d6c1043ec8","observation_id":"932ebb3d-8600-4da0-9145-6ca26b92106b","resolution":{"observed_at":"2026-08-11T23:49:03.428379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.17046","last_updated":"2024-11-26T02:23:31Z","snapshot_observed_at":"2026-08-12T12:32:55.562854Z","submitted_at":"2024-11-26T02:23:31Z","title":"Large-Scale Data-Free Knowledge Distillation for ImageNet via Multi-Resolution Data Generation","version":1},"cited_work":{"arxiv_id":"2411.17046","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.17046","snapshot_observed_at":"2026-08-11T23:49:02.617663Z","title":"Large-Scale Data-Free Knowledge Distillation for ImageNet via Multi-Resolution Data Generation","venue":"cs.CV","work_id":"aea3ddb8-7d7c-48b5-abcb-a3e9276150e8","year":2024},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.454513Z"},"links":{"cited_paper":"/paper/2411.17046","citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:6b599587139e81f20ab401aef8de57ca7ff8e51c3efb445cdcf3adabd8b7f8ae","observation_id":"0ad02cc7-945c-473b-b5a7-c5bd2eae24d1","resolution":{"observed_at":"2026-08-11T23:49:02.625769Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.405382Z","title":"Nayer: Noisy layer data generation for efficient and effective data-free knowl- edge distillation","venue":null,"work_id":"d1c73109-122f-40a6-a645-3e98de4529bb","year":2024},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.462256Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:3745b0330762a937285c012f41d012b187223e1e8e4eb98aef49cc1a240b305e","observation_id":"8179444d-7cbd-4bc0-82c6-83c2d03e7f37","resolution":{"observed_at":"2026-08-11T23:49:03.410579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.386690Z","title":"Meta-dataset: A dataset of datasets for learning to learn from few examples","venue":null,"work_id":"e9ff2876-df47-4eb0-bc63-7277879b0bdc","year":2020},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.468510Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:93c7a1e93bbb040bc6be2bf8871fea7eda888a32c454b69ca36f44d92d59ea7c","observation_id":"f8ecaca5-9874-4888-bd03-6e3cda50cc81","resolution":{"observed_at":"2026-08-11T23:49:03.393273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.368707Z","title":"Matching networks for one shot learning.Ad- vances in neural information processing systems , 29, 2016","venue":null,"work_id":"7b0ade3e-939f-413a-8a5f-e713f506bdfb","year":2016},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.476403Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:5706de0948edb4533d567a2269035950e318c8f9db60b946393cf4a5f4d4d341","observation_id":"9001b451-1bdb-4926-9f7a-aa8a3eb9ab29","resolution":{"observed_at":"2026-08-11T23:49:03.373994Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.349413Z","title":"Transformers learn in-context by gradient descent","venue":null,"work_id":"6d672aee-7a45-4ab2-b5d9-f8cdc37ff645","year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.482501Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:d761197edbbd19c3323e1ea0fb9413eb95fc16b03bc59546c1ab2226d901b229","observation_id":"a388596d-3a7c-42ee-8022-cc48ba878758","resolution":{"observed_at":"2026-08-11T23:49:03.355102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.331678Z","title":"The Caltech-UCSD Birds-200- 2011 Dataset","venue":null,"work_id":"c5c5bf99-32c4-4f4c-9880-6bf74c8de059","year":2011},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.488873Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:ea194e61997e09754aff9e7bee781abf89921fa40726fc5930f2422361008da5","observation_id":"9c432c83-e4e3-4eb6-b477-b82667b308b5","resolution":{"observed_at":"2026-08-11T23:49:03.337131Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.314297Z","title":"Generalizing to unseen domains: A survey on do- main generalization","venue":null,"work_id":"7279f33e-1f42-448b-86ba-9dc33e34ba73","year":2022},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.494305Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:000969ddc18ba3bbc231d4aab6210a4d72abd2f43c1d6244813ea98cffde7a46","observation_id":"449d0797-3a36-4462-a80f-d50725ba3ccf","resolution":{"observed_at":"2026-08-11T23:49:03.319922Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.295708Z","title":"De-confounded data-free knowledge distillation for handling distribution shifts","venue":null,"work_id":"ceadd51f-d2ea-4068-b197-4a7ea5336b98","year":2024},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.500548Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:8c025945afe2b8e33b40420490e1707dd1d122b2b0bdebdc94734d924b514f56","observation_id":"33ed02de-3979-495f-8d79-c48f10ee878a","resolution":{"observed_at":"2026-08-11T23:49:03.301668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:02.505639Z","title":"Meta learning on a sequence of imbalanced domains with difficulty awareness","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.505639Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:34d740cdd72f58574dce646bd14a20ba207a40014ee656134ba19e70bd02b23c","observation_id":"ceaf2101-e809-4f01-a8fe-f897d279ebdf","resolution":{"observed_at":"2026-08-11T23:49:02.505639Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.264208Z","title":"Meta-learning without data via wasserstein distributionally- robust model fusion","venue":null,"work_id":"be8be389-54f5-4d86-91ad-43f59d156a03","year":2022},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.510457Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:94d69b6e9c92466db44d92f4cd67782a6583cc58633cff80f8798045c798d38f","observation_id":"03601704-7229-410a-a2d2-a4adb1c18feb","resolution":{"observed_at":"2026-08-11T23:49:03.269704Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.245678Z","title":"Task groupings regular- ization: Data-free meta-learning with heterogeneous pre- trained models","venue":null,"work_id":"c5c07a9f-31b3-4d24-a017-e81b3cb10dac","year":2024},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.515709Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:e88412f74925036f421a49817607842facaaebffabf49a0121380c832015ad70","observation_id":"e69481af-ecd4-4a12-92e8-23b7ca3cbd2a","resolution":{"observed_at":"2026-08-11T23:49:03.251892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.226262Z","title":"Free: Faster and better data-free meta-learning","venue":null,"work_id":"0ad0c531-9edc-4b5f-a042-ee4c24fc7e07","year":2024},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.521737Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:e35d6a69683167d6751e36e73708703aa97fcb75cfbe7423fbcc89e96dc7749e","observation_id":"fe82fd05-b513-4d59-8ec0-2b9685999930","resolution":{"observed_at":"2026-08-11T23:49:03.232310Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.209312Z","title":"pi-tuning: Transferring multimodal foundation models with optimal multi-task inter- polation","venue":null,"work_id":"21314cf3-07d2-4ba0-af0e-79a0d1b98f4d","year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.526950Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:1569c82b143acfe1c725aba5e0092d7e80c19c810f4a6ebb85fdc90a1c2b865b","observation_id":"1480a2e9-8234-4da5-8788-795281c2a89a","resolution":{"observed_at":"2026-08-11T23:49:03.214334Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.190399Z","title":"Mole: Mixture of lora experts","venue":null,"work_id":"7abaf28f-defa-47bd-83ec-5c0f00be8ac1","year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.532411Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:8d1151695edce37f3af185f1741e0adee7d0c484f54361aa81b997f28f6013e2","observation_id":"ff3a4ad4-5a20-4c68-be03-b081ff19249b","resolution":{"observed_at":"2026-08-11T23:49:03.197254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.170587Z","title":"Meta-personalizing vision- language models to find named instances in video","venue":null,"work_id":"69cf6cdb-6bdd-424b-8718-421e62d2f4a9","year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.537671Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:3c935a6db5d34e9ae2adee2e34f69e0b47ff53f627eea62829ca356798623e78","observation_id":"8d6881d8-eebb-41ee-993b-035f8e2254bf","resolution":{"observed_at":"2026-08-11T23:49:03.176649Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.152475Z","title":"11 Dreaming to distill: Data-free knowledge transfer via deep- inversion","venue":null,"work_id":"a33d9955-1231-4129-90df-ac93f25801a5","year":2020},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.542981Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:c155e8f8d7944ec07bcd05417a4dbab5a53747331da8aebfe723a07fd8809c9e","observation_id":"8fee081b-75ed-4feb-9cc7-e8e1ccf8f167","resolution":{"observed_at":"2026-08-11T23:49:03.157971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.134473Z","title":"Bayesian model-agnostic meta-learning","venue":null,"work_id":"3b39facd-70f0-46ab-a083-34657a379a7d","year":2018},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.548707Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:f20d2df1d6592dae2cf498c965980480cd612a8ec438f9860216610e18dbd183","observation_id":"ba09bb1e-f0a7-450d-8ee7-f58cb2be3da3","resolution":{"observed_at":"2026-08-11T23:49:03.140780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.113390Z","title":"Data-free knowledge distillation via feature exchange and activation region constraint","venue":null,"work_id":"d37fd1ce-732a-48ea-9169-f51e1e2f2d82","year":2023},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.554557Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:6a6e7475fa62e8e21f1347e9b3655756090efee5dea3d266a3f991e5e9685ddc","observation_id":"fb429769-24eb-4211-acad-35c833b74666","resolution":{"observed_at":"2026-08-11T23:49:03.119951Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.094244Z","title":"recycle in-domain LoRAs","venue":null,"work_id":"bacc7b88-e432-4198-b04a-c0ef354c478d","year":2024},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.559610Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:bd7afeda25529177adb0246266e2632ae7e5b8ed18b8ed120d5ffb75d65e4c79","observation_id":"8e0c5053-03fe-4f80-be6e-5286445c7357","resolution":{"observed_at":"2026-08-11T23:49:03.099626Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:49:03.075442Z","title":null,"venue":null,"work_id":"02051b28-ceaf-4f55-a890-e8db7d91364c","year":null},"citing_paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-11T23:49:02.568731Z"},"links":{"citing_paper":"/paper/2412.02220"},"observation_digest":"sha256:6d6f8f8bdd7a6c7e28b78856eb0e828f2876bbcdc39d6e17e883b069e7b240c9","observation_id":"8148cc35-cdda-462a-8523-40df5a658ba6","resolution":{"observed_at":"2026-08-11T23:49:03.081209Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.02220","last_updated":"2024-12-03T07:25:30Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T20:33:39.924177Z","submitted_at":"2024-12-03T07:25:30Z","title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs"},"reference_resolution":{"displayed":75,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":22,"verified_exact":4,"verified_fuzzy":48},"total_outbound_references":75},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 75 of 75 outbound references and 0 inbound Pith citation observations for arXiv:2412.02220."}