{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:18:36Z","timestamp":1778051916729,"version":"3.51.4"},"reference-count":88,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00126","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1231-1241","source":"Crossref","is-referenced-by-count":0,"title":["Model-free Domain Adaptation for Concealed Multimodal Large-Language Models"],"prefix":"10.1109","author":[{"given":"Yu","family":"Mitsuzumi","sequence":"first","affiliation":[{"name":"NTT, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akisato","family":"Kimura","sequence":"additional","affiliation":[{"name":"NTT, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hisashi","family":"Kashima","sequence":"additional","affiliation":[{"name":"Kyoto University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"Introducing gpt-4.5","year":"2025"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref4","article-title":"The claude 3 model family: Opus, sonnet, haiku","year":"2024","journal-title":"Claude-3 Model Card"},{"key":"ref5","article-title":"Exploring visual prompts for adapting large-scale models","author":"Bahng","year":"2022"},{"key":"ref6","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref7","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/285"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00039"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00704"},{"key":"ref11","first-page":"1081","article-title":"Transferability vs. discriminability: Batch spectral penalization for adversarial domain adaptation","volume-title":"Proc. ICML","author":"Chen"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3418776"},{"issue":"240","key":"ref13","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"JMLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00444"},{"issue":"59","key":"ref17","first-page":"1","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"JMLR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_36"},{"key":"ref20","article-title":"How well can vision language models see image details?","author":"Gou","year":"2024"},{"key":"ref21","article-title":"Source free domain adaptation with image translation","author":"Hou","year":"2020"},{"key":"ref22","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"Proc. ICML","author":"Houlsby"},{"key":"ref23","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00521"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02310"},{"key":"ref28","first-page":"5468","article-title":"Understanding self-training for gradual domain adaptation","volume-title":"Proc. ICML","author":"Kumar"},{"key":"ref29","first-page":"12365","article-title":"Confidence score for source-free unsupervised domain adaptation","volume-title":"Proc. ICML","author":"Lee"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01500"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.591"},{"key":"ref33","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. ICML","author":"Li"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00966"},{"key":"ref35","first-page":"6028","article-title":"Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation","volume-title":"Proc. ICML","author":"Liang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00784"},{"key":"ref37","first-page":"1","article-title":"A comprehensive survey on test-time adaptation under distribution shifts","author":"Liang","year":"2024","journal-title":"IJCV"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00738"},{"key":"ref39","first-page":"22968","article-title":"Cycle self-training for domain adaptation","volume-title":"Proc. NeurIPS","author":"Liu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref41","article-title":"Llava-next: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref42","first-page":"21808","article-title":"Ttt++: When does self-supervised test-time training fail or thrive?","volume-title":"Proc. NeurIPS","author":"Liu"},{"key":"ref43","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","volume-title":"Proc. ICML","author":"Long"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02694"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.17"},{"key":"ref46","article-title":"Kl guided domain adaptation","volume-title":"Proc. ICLR","author":"Nguyen"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02320"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00149"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1447"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/402"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_10"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02202"},{"key":"ref53","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.04.003"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_16"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00392"},{"key":"ref57","article-title":"Gradient matching for domain generalization","volume-title":"Proc. ICLR","author":"Shi"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.259"},{"key":"ref60","first-page":"20841","article-title":"Black-box tuning for language-model-as-a-service","volume-title":"Proc. ICML","author":"Sun"},{"key":"ref61","first-page":"9229","article-title":"Test-time training with self-supervision for generalization under distribution shifts","volume-title":"Proc. ICML","author":"Sun"},{"key":"ref62","article-title":"Gemini: a family of highly capable multimodal models","author":"Anil","year":"2023"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2021.3111034"},{"key":"ref64","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref65","article-title":"Deep domain confusion: Maximizing for domain invariance","author":"Tzeng","year":"2014"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00367"},{"key":"ref69","article-title":"Unleashing the power of visual prompting at the pixel level","author":"Wu","year":"2024","journal-title":"TMLR"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00888"},{"key":"ref71","first-page":"29393","article-title":"Exploiting the intrinsic neighborhood structure for source-free domain adaptation","volume-title":"Proc. NeurIPS","author":"Yang"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00885"},{"key":"ref73","first-page":"5802","article-title":"Attracting and dispersing: A simple approach for source-free domain adaptation","volume-title":"Proc. NeurIPS","author":"Yang"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01081"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00400"},{"key":"ref78","article-title":"On the out-of-distribution generalization of multimodal large language models","author":"Zhang","year":"2024"},{"key":"ref79","first-page":"7404","article-title":"Bridging theory and algorithm for domain adaptation","volume-title":"Proc. ICML","author":"Zhang"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00736"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02508"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0371"},{"key":"ref83","article-title":"Learning with local and global consistency","volume-title":"Proc. NeurIPS","author":"Zhou"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_28"},{"key":"ref86","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. ICLR","author":"Zhu"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_18"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00608"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492000.pdf?arnumber=11492000","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:31:57Z","timestamp":1778049117000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492000\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":88,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00126","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}