{"as_of":"2026-08-15T17:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:76012d2ef0d34ef4f46201ff521ab576654514c48a7e21e8f26b4a3f51cf6607","coverage":[{"denominator":59,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":59,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T21:44:33.156476Z","state":"measured"},{"denominator":59,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":59,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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/2501.04293/citation-record","integrity":"/paper/2501.04293/integrity","json":"/paper/2501.04293/citation-record.json","paper":"/paper/2501.04293"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:44:33.986656Z","title":"Mtlora: Low-rank adaptation approach for efficient multi-task learn- ing","venue":null,"work_id":"f26b8ddf-bdf8-4d2f-b24e-972892b0cab0","year":null},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:32.940383Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:3a21d1f3154f113cbf85b7ea2c0ffb2e86fea66ce02fac90853875e10b5a1bae","observation_id":"e2d1f00e-0646-43dd-acc5-1fed87f12dd7","resolution":{"observed_at":"2026-08-10T21:44:33.991541Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1808.06876","last_updated":"2019-01-14T09:05:47Z","snapshot_observed_at":"2026-08-14T18:38:53.354521Z","submitted_at":"2018-08-21T12:52:03Z","title":"Adversarial training for multi-context joint entity and relation extraction","version":3},"cited_work":{"arxiv_id":"1808.06876","doi":null,"metadata_source":"pith","pith_arxiv_id":"1808.06876","snapshot_observed_at":"2026-08-10T21:44:33.465733Z","title":"Adversarial training for multi-context joint entity and relation extraction","venue":"cs.CL","work_id":"bea605bd-6e6c-4401-89ba-bef7fbbeb035","year":2018},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:32.945137Z"},"links":{"cited_paper":"/paper/1808.06876","citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:5673fb4bf45e40861f258dce01778e32c9041517af99d6ecd326034d4bc2c504","observation_id":"87283ebc-d1d8-46b5-b199-d4b8b63d9b3b","resolution":{"observed_at":"2026-08-10T21:44:33.469804Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.974499Z","title":"Mult: An end-to-end multitask learning transformer","venue":null,"work_id":"539134c8-f773-41b0-9075-055377619fb9","year":2022},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:32.949282Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:c84772bdea89e054d7a87de07c0938b22c3831999adcd814016f8fc87a282aeb","observation_id":"eaaea12c-dcf0-4db2-95be-133f8e715a79","resolution":{"observed_at":"2026-08-10T21:44:33.978991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.963176Z","title":"Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al","venue":null,"work_id":"677639b7-6ff2-4257-8cf2-657e33c9ecac","year":2020},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:32.953436Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:6097ae80c1dcd4659e6f4d86a9769e358f75174a94e0c9d58c0bb612327f1eb4","observation_id":"cea52191-b645-4a3b-978e-a5ea3eb6784a","resolution":{"observed_at":"2026-08-10T21:44:33.967065Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:32.957501Z","title":"End-to- end object detection with transformers","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:32.957501Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:1fcf37ea7aa100340c203bd1a87f712eb972ae415c855e10d780ce5434929d01","observation_id":"fa43d396-774e-40d5-8e91-b1dbc9adb2da","resolution":{"observed_at":"2026-08-10T21:44:32.957501Z","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":"2026-08-10T21:44:33.945139Z","title":"Adapter configuration: Both sequential and parallel configurations are possible in adapter-based PEFT framework [7]","venue":null,"work_id":"740932a5-d6b6-4d1f-9637-9b3d0ed83215","year":2018},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:32.961516Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:0ef6366565d19eb4cd3670501d5365749f4c469fdb32bc25c9d458c1649ea352","observation_id":"075574ab-7832-417d-974b-befbcb32eebe","resolution":{"observed_at":"2026-08-10T21:44:33.949261Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.933706Z","title":"Adaptformer: Adapting vision transformers for scalable visual recogni- tion","venue":null,"work_id":"bfa1c93e-c086-40be-b57d-e290b1a1f138","year":2022},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:32.965160Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:c751bc091fe54c38c021115e613327b32f19b844292f71e6ef0902933884f512","observation_id":"8b0ed744-c519-4181-866f-1200ec628f44","resolution":{"observed_at":"2026-08-10T21:44:33.937823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19104","last_updated":"2024-12-26T07:47:20Z","snapshot_observed_at":"2026-08-12T03:51:21.211579Z","submitted_at":"2024-12-26T07:47:20Z","title":"Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models","version":1},"cited_work":{"arxiv_id":"2412.19104","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.19104","snapshot_observed_at":"2026-08-10T21:44:33.449281Z","title":"Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models","venue":"cs.CV","work_id":"cd40a658-770d-48aa-a3e6-fbdf60cd354b","year":2024},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:32.969001Z"},"links":{"cited_paper":"/paper/2412.19104","citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:ac1301abc76d432174ef5b2a90abd054bbaea39a5597d06b481fc19485376190","observation_id":"b261d85d-9469-407c-83b5-0640b749b916","resolution":{"observed_at":"2026-08-10T21:44:33.453634Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.08330","last_updated":"2024-04-12T08:46:53Z","snapshot_observed_at":"2026-08-15T02:40:32.196612Z","submitted_at":"2024-04-12T08:46:53Z","title":"Emerging Property of Masked Token for Effective Pre-training","version":1},"cited_work":{"arxiv_id":"2404.08330","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.08330","snapshot_observed_at":"2026-08-10T21:44:33.430801Z","title":"Emerging Property of Masked Token for Effective Pre-training","venue":"cs.CV","work_id":"336bf21b-8e7f-4a28-a5c3-2b3659600d83","year":2024},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:32.972840Z"},"links":{"cited_paper":"/paper/2404.08330","citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:1fc40b946f923850a68855ee19db0ea42eacf34ae6f619285e6378826e960363","observation_id":"ce28e600-562b-4201-bfc8-4667d1ec0a03","resolution":{"observed_at":"2026-08-10T21:44:33.437178Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.920619Z","title":"Salience-based adaptive masking: revisit- ing token dynamics for enhanced pre-training","venue":null,"work_id":"04136dc1-3fd5-460b-a6d0-5c9963a531bc","year":null},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:32.976841Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:a4f11ec9525a8c1acd223108666adc9ec46af347fdd63daf776fe957e85d5360","observation_id":"555a42c4-dc00-4545-8245-51fe916e1ad6","resolution":{"observed_at":"2026-08-10T21:44:33.924859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:32.980549Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:32.980549Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:de42b967643907ed02bc51e346e04bb1834f6751df940dbb1ae2ae3163283579","observation_id":"41fbb113-0e05-4434-b52b-6b5ef1085f4e","resolution":{"observed_at":"2026-08-10T21:44:32.980549Z","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":"2026-08-10T21:44:33.900601Z","title":"Bert: Pre-training of deep bidirectional trans- formers for language understanding","venue":null,"work_id":"d2dded50-fcb1-487d-b145-5f9aa5ce62f2","year":2018},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:32.984446Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:dfe827644c87ddbb617145b0c205082e248fe7d0472b3e032bcf5e855090bfc0","observation_id":"1fac4f65-4f2d-4dd6-9b29-576d61659e19","resolution":{"observed_at":"2026-08-10T21:44:33.904861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:32.988123Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:32.988123Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:0cbc508c92b869c2f50ee80870d9591abdd8c829c576f91dbea71dfcd9e5b0ef","observation_id":"5d6d5b2a-78a9-4ecf-8a9a-5593179d2795","resolution":{"observed_at":"2026-08-10T21:44:32.988123Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.15010","last_updated":"2023-04-28T17:59:25Z","snapshot_observed_at":"2026-08-12T23:40:42.885633Z","submitted_at":"2023-04-28T17:59:25Z","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.15010","snapshot_observed_at":"2026-08-10T21:44:32.991757Z","title":"Llama-adapter v2: Parameter-efficient vi- sual instruction model","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:32.991757Z"},"links":{"cited_paper":"/paper/2304.15010","citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:4d47a913437574e3a70831814f068a18f6f95bf40cdd937b224f8fca9a3fb7c8","observation_id":"27034311-7c15-4207-b1b6-cf20bab0cfe4","resolution":{"observed_at":"2026-08-10T21:44:32.991757Z","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":"2026-08-10T21:44:33.882218Z","title":null,"venue":null,"work_id":"78cca026-3171-4bbf-bb88-ddda04380a2b","year":2019},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:32.995885Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:41b142b37cc59a5e92261baf5a21f33fd7c19344972f7790d909bc174611286a","observation_id":"5b0ef349-aecc-491c-ad73-f91384e440d0","resolution":{"observed_at":"2026-08-10T21:44:33.886231Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.869220Z","title":"Sensitivity-aware visual parameter-efficient fine-tuning","venue":null,"work_id":"38daa9bd-90ba-4a92-93a6-53d4e443d578","year":2023},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:32.999135Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:0476808e63f775c5624f788ac4f0ae84cdc51729d1fb54aa8e435dc04865fece","observation_id":"3493d7f9-08eb-4fa7-8170-a74528fdf578","resolution":{"observed_at":"2026-08-10T21:44:33.874143Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.04366","last_updated":"2022-02-02T16:39:23Z","snapshot_observed_at":"2026-08-13T17:56:57.877812Z","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":"2026-08-10T21:44:33.002766Z","title":"Towards a unified view of parameter-efficient transfer learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.002766Z"},"links":{"cited_paper":"/paper/2110.04366","citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:54e8c437e366764a7d60663fdb61e1aea7c6442e85fc68358dff65384fc66499","observation_id":"33c166ef-c633-4a6b-82f8-c330d137feed","resolution":{"observed_at":"2026-08-10T21:44:33.002766Z","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":"2026-08-10T21:44:33.856052Z","title":"Masked autoencoders are scalable vision learners","venue":null,"work_id":"9aabeb20-858c-48ad-88dd-6383dcdd6809","year":2022},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.006853Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:21f269d2dec23cd164317e2e15f21af4d703d643c42168c6e89a41d88606fa0c","observation_id":"c996c90a-f3ed-49b2-8445-d829080af528","resolution":{"observed_at":"2026-08-10T21:44:33.860629Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.010598Z","title":"Masked autoencoders are scalable vision learners","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.010598Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:c45b5b196ee399c7ecb65064fc80fa648cb6bd0ffeab9e79de3b15828f6ee434","observation_id":"f54d0176-5946-4be5-8790-29ee6acc9c70","resolution":{"observed_at":"2026-08-10T21:44:33.010598Z","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":"2026-08-10T21:44:33.837711Z","title":"Parameter-efficient transfer learning for nlp","venue":null,"work_id":"fe048a08-bb05-47bd-a0a0-bcde08de9370","year":2019},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.014690Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:4f393adbc352ab9714c7ae2264c6a9db08e9f168e44eeae956e416e84dc36e9f","observation_id":"e8c28877-36eb-4d7e-869b-1eae4960b62b","resolution":{"observed_at":"2026-08-10T21:44:33.841504Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-10T21:44:33.018398Z","title":"Hu et al","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.018398Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:fccd9756d196b0815e93dd7c772242d61fe027d6b7061c4d23396c3af8112107","observation_id":"654463ab-93e2-4e88-b3ab-9950baf6b770","resolution":{"observed_at":"2026-08-10T21:44:33.018398Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.01933","last_updated":"2023-10-09T15:38:46Z","snapshot_observed_at":"2026-08-13T12:09:20.320930Z","submitted_at":"2023-04-04T16:31:37Z","title":"LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.01933","snapshot_observed_at":"2026-08-10T21:44:33.022023Z","title":"Llm-adapters: An adapter family for parameter- efficient fine-tuning of large language models.arXiv preprint arXiv:2304.01933, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.022023Z"},"links":{"cited_paper":"/paper/2304.01933","citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:0701b62b4fc35c259706254ebd3a639c24a1f9768aabcfd1242099c8a3f383ac","observation_id":"49b4a238-22af-435d-8a9d-877ff443d298","resolution":{"observed_at":"2026-08-10T21:44:33.022023Z","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":"2026-08-10T21:44:33.825149Z","title":"Going beyond multi-task dense pre- diction with synergy embedding models","venue":null,"work_id":"aaf51ad3-3f94-4c98-a0b3-7ad7e18913f5","year":2024},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.026103Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:9b6fdc0916c24fb1656dca6aada152726bb6fcff067fed75608d38f019a7c5fe","observation_id":"d79c3bc3-6db3-4b66-aad2-11ef8c954419","resolution":{"observed_at":"2026-08-10T21:44:33.829620Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.811752Z","title":"Vi- sual prompt tuning","venue":null,"work_id":"961a55a8-0b1e-4f06-823f-b7b9623afcbe","year":2022},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.029771Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:4dfcb28a76969014b1511c9eaf5c081370f52cf1d0678a97b909d619f9fec4a2","observation_id":"5e3fb4b0-2761-4e30-9651-f509bcd29c17","resolution":{"observed_at":"2026-08-10T21:44:33.816814Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.033562Z","title":"Dynamic filter networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.033562Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:7693fbb810e3d38d43ca6ea2ec3eba46523a5bdc0a18e9269d10ddf2f55362db","observation_id":"5f2c2645-5f9f-4a44-ac15-f40f0ff3323f","resolution":{"observed_at":"2026-08-10T21:44:33.033562Z","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":"2026-08-10T21:44:33.789207Z","title":"Compacter: Efficient low-rank hypercomplex adapter layers","venue":null,"work_id":"81ef7349-c6e3-425a-a855-3c4699aac4d9","year":2021},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.037176Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:ca24f9e43f0320f2ed61b8222c5bc2458150fecf57c9ad1ce44968682aa6ebb4","observation_id":"829b335d-b16e-439a-bfc0-54863158029f","resolution":{"observed_at":"2026-08-10T21:44:33.794742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.04489","last_updated":"2021-06-08T16:16:40Z","snapshot_observed_at":"2026-08-13T19:07:44.039577Z","submitted_at":"2021-06-08T16:16:40Z","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.04489","snapshot_observed_at":"2026-08-10T21:44:33.040770Z","title":"Parameter-efficient multi-task fine-tuning for transformers via shared hypernetworks.arXiv preprint arXiv:2106.04489, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.040770Z"},"links":{"cited_paper":"/paper/2106.04489","citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:600e35f61a507c40ec8800b00ee21524a9ac5ffe333f6b1b38644771914c1e04","observation_id":"15a87927-17bf-4e22-8138-0e7f0c7667e3","resolution":{"observed_at":"2026-08-10T21:44:33.040770Z","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":"2026-08-10T21:44:33.776874Z","title":"Multi-task learning using uncertainty to weigh losses for scene geome- try and semantics","venue":null,"work_id":"20d14b5c-e8a7-41bb-9b9e-7040215af0c1","year":2018},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.044888Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:5bc85c7ff9f894f2692649d4787ed252eddd6321a27cbea87fef17d6ef37882f","observation_id":"c2a34e9a-260c-4a73-867a-b08e281c89a9","resolution":{"observed_at":"2026-08-10T21:44:33.781222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.764618Z","title":"Sequen- tial cross attention based multi-task learning","venue":null,"work_id":"a744c4b1-e111-4792-ad03-281cc669410b","year":2022},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.048319Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:7e8ae86603de3198b2f6394d1b6e49da12e6fd02943a27b6c65a9bc4d360dd23","observation_id":"c72ee683-931d-4e3d-93f8-21a82280ae4f","resolution":{"observed_at":"2026-08-10T21:44:33.768633Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.753136Z","title":"Knn local attention for image restoration","venue":null,"work_id":"8dd9a298-2f6f-474a-8c2b-bcef967b15f7","year":2022},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.051760Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:e04c7e44dafee33e5e39363f9ce5892bc58028fc2c4d74708f17cce7929c9be8","observation_id":"f0e530d7-e891-4799-97cf-010bf783ae7d","resolution":{"observed_at":"2026-08-10T21:44:33.757153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.740883Z","title":"Cross-scale knn image transformer for image restoration","venue":null,"work_id":"9770a958-016e-48ac-8bd3-7ec0e49b4eca","year":2023},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.055180Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:9210c99fab656457ae94042d807093992bec9222ea06181a1cd6be92f37d6d7b","observation_id":"f487e660-ab56-488d-be40-9379ec438ab9","resolution":{"observed_at":"2026-08-10T21:44:33.744970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.728066Z","title":"Conditional adapters: Parameter-efficient transfer learning with fast in- ference","venue":null,"work_id":"08cb1e16-a4e7-49b3-831c-d874f7214cd8","year":2023},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.058769Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:dbc6a4e2055db0afafa9bbb4658019364ec3fd403c2898668e6c536169c4814d","observation_id":"d11cd5f5-7135-4812-82ef-1bdca13d4403","resolution":{"observed_at":"2026-08-10T21:44:33.732218Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08691","last_updated":"2021-09-02T17:34:41Z","snapshot_observed_at":"2026-08-06T15:24:34.790850Z","submitted_at":"2021-04-18T03:19:26Z","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08691","snapshot_observed_at":"2026-08-10T21:44:33.062224Z","title":"The power of scale for parameter-efficient prompt tuning.arXiv preprint arXiv:2104.08691, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.062224Z"},"links":{"cited_paper":"/paper/2104.08691","citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:74603f024114153473069f2f684b13945c185a6e2f6c51fa7234be3f1c7bf80d","observation_id":"1b33c386-37d1-4c01-a8b8-94506c2eab00","resolution":{"observed_at":"2026-08-10T21:44:33.062224Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.00190","last_updated":"2021-01-01T08:00:36Z","snapshot_observed_at":"2026-08-12T12:37:28.207761Z","submitted_at":"2021-01-01T08:00:36Z","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.00190","snapshot_observed_at":"2026-08-10T21:44:33.065943Z","title":"Prefix-tuning: Optimiz- ing continuous prompts for generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.065943Z"},"links":{"cited_paper":"/paper/2101.00190","citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:6dbfbaf27f65ddd4d236cbaf0ac85fea7234f14542997e48baa65a73653d6b54","observation_id":"3e5cff21-5c60-432c-9458-d6227622cf97","resolution":{"observed_at":"2026-08-10T21:44:33.065943Z","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":"2026-08-10T21:44:33.716863Z","title":"Polyhistor: Parameter-efficient multi-task adap- tation for dense vision tasks","venue":null,"work_id":"858ceeaa-1630-4154-bad7-26fbb85999fc","year":2022},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.070776Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:cbeaa3dad3e9a1598eb4934fd03b7af5a1a399276cf8a9c58fb34320b4e969cf","observation_id":"9132a85f-5357-4a7f-a2a8-bb3cc21d0857","resolution":{"observed_at":"2026-08-10T21:44:33.720914Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.705855Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":"c1187260-c69f-4786-8b26-9def5e420433","year":2021},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.074615Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:b5fdb4b2aad26baaec63e1fd8781c126e3ad2dffdaa867b8a4d71d8387c2a0ed","observation_id":"16cbf5fb-05ed-4364-b196-b5a60e783ba1","resolution":{"observed_at":"2026-08-10T21:44:33.709790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.694290Z","title":"Swin trans- former: Hierarchical vision transformer using shifted win- dows, 2021","venue":null,"work_id":"f0cbd420-7abb-4d99-ac72-a2633e12578f","year":2021},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.078199Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:6f53942dea3dcda45c2854bbc3b7021d3c76861f4d62c36ca8bfc1f4c55d08d5","observation_id":"fe578684-1556-49f1-8b4c-044f16a982e4","resolution":{"observed_at":"2026-08-10T21:44:33.698323Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.682612Z","title":"Swin transformer v2: Scaling up capacity and resolution","venue":null,"work_id":"89575d6c-83c8-4469-9101-08d5a5dd3e63","year":2022},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.081941Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:d12b567821cb45a3d4f039bbfb203fba886ad82ee8f4391fb797c51d4f3a29ec","observation_id":"592d777f-cbcb-448a-ac25-e80e599d4213","resolution":{"observed_at":"2026-08-10T21:44:33.686561Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.085440Z","title":"Vi- sion transformers for dense prediction","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.085440Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:ce28b6398d7b88a427e880aaba160ccba87820e57544c3492815b07bc0c5ca81","observation_id":"26731d1a-e4ef-4f5a-8330-b99eaf0593cd","resolution":{"observed_at":"2026-08-10T21:44:33.085440Z","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":"2026-08-10T21:44:33.088648Z","title":"Grad-cam: Visual explanations from deep networks via gradient-based localization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.088648Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:16e01ad672fd38af1d56d6a10804d066e64ad7bbd81d452918a7a53c61e9a312","observation_id":"55e87337-4db2-4f50-8977-36dacefb5e80","resolution":{"observed_at":"2026-08-10T21:44:33.088648Z","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":"2026-08-10T21:44:33.658326Z","title":"Multi-task learning as multi-objective optimization","venue":null,"work_id":"2505b918-2314-49b0-a89b-4a3b462aba94","year":2018},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.092202Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:923ec0bcfc3b4f7cda8156fe4820c96ba2a5c6f117c41c4d59a2631597ea6fb5","observation_id":"eee3afc1-f5e6-4a57-a1c5-1d5ee5fd387a","resolution":{"observed_at":"2026-08-10T21:44:33.662199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.095647Z","title":"Deep high-resolution representation learning for human pose es- timation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.095647Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:6dbcb58eafa83ae06332b477c09a2098010570ecfe37dd2934de9ab557a47426","observation_id":"f0fd44b8-e465-4a6d-8fdd-c5fccb23a8d9","resolution":{"observed_at":"2026-08-10T21:44:33.095647Z","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":"2026-08-10T21:44:33.639350Z","title":"VL-Adapter: Parameter-efficient transfer learning for vision-and-language tasks","venue":null,"work_id":"acb7c502-e7c7-4240-b9b5-c36054877b5c","year":null},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.099352Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:b57538116be8f673f6714cdcfce41472e8cd4f0dd8fcf728d584592682101f2e","observation_id":"a49f63ed-5c77-482b-a032-71dab6fc3c09","resolution":{"observed_at":"2026-08-10T21:44:33.644102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.627049Z","title":"Mti-net: Multi-scale task interaction networks for multi-task learning","venue":null,"work_id":"2366ea24-2191-4b2e-ba40-eae0a027d12d","year":2020},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.103299Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:a022099e63e218f1c4a0173a1cd0481fd624aa9fb2faaed4cc627fcee2413e28","observation_id":"1195d158-0309-4247-95a7-a605555280fd","resolution":{"observed_at":"2026-08-10T21:44:33.631130Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.615314Z","title":"Multi-task learning for dense prediction tasks: A survey","venue":null,"work_id":"7fc6907f-3eb1-4b3b-be34-64e205f4a1f2","year":2021},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.106958Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:0abee918940cc994d3ed4a8c884d57c06b6ed0ba43108286d0e4fcbce384fae3","observation_id":"af29ca17-6569-4923-aaba-82189cd99f28","resolution":{"observed_at":"2026-08-10T21:44:33.619412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.110565Z","title":"Segformer: Simple and efficient design for semantic segmentation with transform- ers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.110565Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:e90d31cb91510cd587927f244c12bdd709e8e573ec0281a2a830ed5456e43919","observation_id":"62a542c8-c89a-471f-b77b-ac02f7129884","resolution":{"observed_at":"2026-08-10T21:44:33.110565Z","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":"2026-08-10T21:44:33.596117Z","title":"Segformer: Simple and efficient design for semantic segmentation with transform- ers","venue":null,"work_id":"b2a13a05-a39e-47d1-931d-7b53dda072ed","year":2021},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.114219Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:5a002f472bc1c1eb777c0028ad8e15201c72bd9853104faa993caeba32f2b51a","observation_id":"56b35b73-892e-44f5-8c60-3c8b6532b94e","resolution":{"observed_at":"2026-08-10T21:44:33.599977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.585447Z","title":"Simmim: A simple framework for masked image modeling","venue":null,"work_id":"c4d50867-e7e3-4898-8450-9cbda0da7c67","year":2022},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.117996Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:b7a783528cac863c99b8cb446ed1a6d2b872feefb2ac7fb37d9447f09919baa9","observation_id":"efd18738-0a02-414b-a0aa-81c03144752b","resolution":{"observed_at":"2026-08-10T21:44:33.589213Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.573273Z","title":"Vmt-adapter: Parameter-efficient transfer learning for multi- task dense scene understanding","venue":null,"work_id":"a903287f-0931-4fd4-a632-0f5e2bce33ce","year":null},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.121566Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:7b7c5d29e19d6e711c8e4eb627ae4e899710a777b092b0a3d5f8fba2093f9879","observation_id":"e29a2e57-eb5e-4691-af41-58ac49d67cce","resolution":{"observed_at":"2026-08-10T21:44:33.578096Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.560576Z","title":"Multi-task dense prediction via mixture of low-rank experts","venue":null,"work_id":"cea2719c-dfbb-42c1-a825-76e629572dc0","year":2024},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.124944Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:0ef7ec81711f3bb3359954542eb0fad502a8f6e1f6603c8140d5c244cc51b4ea","observation_id":"8465666e-ed9d-4b86-8356-d69254683b4e","resolution":{"observed_at":"2026-08-10T21:44:33.564843Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.549001Z","title":"Taskprompter: Spatial-channel multi-task prompting for dense scene understanding","venue":null,"work_id":"20a6f935-ce5b-4b64-bd80-7b0d6e11d647","year":2022},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.128309Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:0f39ec843c64e94261611480a56788c49002623249c4199abd3e416bb8554852","observation_id":"4a7d19c2-0954-47e5-894f-276d545fd622","resolution":{"observed_at":"2026-08-10T21:44:33.553237Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.536595Z","title":"Taskexpert: Dynamically assem- bling multi-task representations with memorial mixture-of- experts","venue":null,"work_id":"2a3d7ab4-69fd-4cb9-ab30-d8313659bdc1","year":2023},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.131914Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:6f01b1d7ae6a04cc58cdeee573d17edcb9594b7865da08f24b773409b39b668b","observation_id":"0aa5d2fa-0c72-458b-8763-fde84cdde5c8","resolution":{"observed_at":"2026-08-10T21:44:33.541000Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.09616","last_updated":"2023-01-29T06:15:39Z","snapshot_observed_at":"2026-08-13T15:40:42.113113Z","submitted_at":"2022-05-19T15:22:29Z","title":"Masked Image Modeling with Denoising Contrast","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.09616","snapshot_observed_at":"2026-08-10T21:44:33.135128Z","title":"Masked image modeling with denoising contrast","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.135128Z"},"links":{"cited_paper":"/paper/2205.09616","citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:739e879eb40fa304adf53e32f96cbc9f53026a6fbfd7d628125146edecfb2aca","observation_id":"70a5b5e3-faa7-4cb3-b202-6f1468d9c7d7","resolution":{"observed_at":"2026-08-10T21:44:33.135128Z","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":"2026-08-10T21:44:33.524302Z","title":"1% vs 100%: Parameter-efficient low rank adapter for dense predictions","venue":null,"work_id":"58b2d52c-aeca-42b2-b696-8c4ebfef7191","year":2023},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.139037Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:af884f1d94e8e76969695b1902242eb3ec41197529a78a169b4654e9d6022aeb","observation_id":"efcfc607-14ec-468b-948a-801ad3b280cf","resolution":{"observed_at":"2026-08-10T21:44:33.529080Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.142442Z","title":"Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.142442Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:4825bcb930f5b8d62ae7ad8fe6b2ea2aab7039ccf65784c4e4de86d218307574","observation_id":"78b2a88e-60a9-4d74-a99a-edafbf65bb5f","resolution":{"observed_at":"2026-08-10T21:44:33.142442Z","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":"2026-08-10T21:44:33.512340Z","title":"Zamir, Alexander Sax, William Shen, Leonidas J","venue":null,"work_id":"b2331f77-a4a6-4fe5-95ae-e8c6fc006828","year":2018},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.146166Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:e28c097254d79ce41a15bdca0ccf9f334d21134bf54edd014bf5bcca31d925c1","observation_id":"cc0dc39e-e00d-43f4-a4c5-e18dca891d6e","resolution":{"observed_at":"2026-08-10T21:44:33.516120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.501593Z","title":"A survey on multi-task learning","venue":null,"work_id":"7b34c19a-9599-4dc5-83ba-7d736f54331c","year":2021},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.149516Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:8ee77e3a478471529d3c6938b06545dbedf0288d5014d16afd259b2151c1bf84","observation_id":"4f778180-523b-45d9-8200-5057bbcba6f7","resolution":{"observed_at":"2026-08-10T21:44:33.505276Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.488828Z","title":"Convolution meets lora: Parameter efficient finetuning for segment anything model","venue":null,"work_id":"de9c8ad6-7118-46bd-a626-997bf94c8474","year":null},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.153020Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:35300ecef2f36c90ea556990cc20afdb7d6aab82be1d5cdbc3096d37d86473a1","observation_id":"94016eea-a49f-4e2b-937f-f6dfa3923419","resolution":{"observed_at":"2026-08-10T21:44:33.493070Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:44:33.477501Z","title":"Decoupled dynamic filter networks","venue":null,"work_id":"6b21266e-1040-40c1-a1c6-b8cd8698adc1","year":2021},"citing_paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-10T21:44:33.156476Z"},"links":{"citing_paper":"/paper/2501.04293"},"observation_digest":"sha256:bc8c6910e517f22f84c8aa70f2849501ec53a592ce2e33ca1ee4fbe0ac53807e","observation_id":"5bc86606-f49c-4615-b901-9b274a398e08","resolution":{"observed_at":"2026-08-10T21:44:33.481549Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.04293","last_updated":"2025-03-28T05:13:50Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-15T01:51:20.054743Z","submitted_at":"2025-01-08T05:35:07Z","title":"TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning"},"reference_resolution":{"displayed":59,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":3,"verified_fuzzy":37},"total_outbound_references":59},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 0 inbound Pith citation observations for arXiv:2501.04293."}