{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:16:54Z","timestamp":1778051814997,"version":"3.51.4"},"reference-count":26,"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\/wacv61042.2026.00338","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"3462-3471","source":"Crossref","is-referenced-by-count":0,"title":["Language Integration in Fine-Tuning Multimodal Large Language Models for Image-Based Regression"],"prefix":"10.1109","author":[{"given":"Roy H.","family":"Jennings","sequence":"first","affiliation":[{"name":"Samsung Israel R&D Center,Tel-Aviv,Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Genady","family":"Paikin","sequence":"additional","affiliation":[{"name":"Samsung Israel R&D Center,Tel-Aviv,Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roy","family":"Shaul","sequence":"additional","affiliation":[{"name":"Samsung Israel R&D Center,Tel-Aviv,Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evgeny","family":"Soloveichik","sequence":"additional","affiliation":[{"name":"Samsung Israel R&D Center,Tel-Aviv,Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00373"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967829"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00968"},{"key":"ref5","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"Int. Conf. Mach. Learn","author":"Kim"},{"key":"ref6","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00406"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01832"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3319020"},{"key":"ref10","article-title":"Deepfl-iqa: Weak supervision for deep iqa feature learning","author":"Lin","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref12","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.532"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00644"},{"key":"ref16","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Int. Conf. Mach. Learn","author":"Radford"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2831899"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3233\/IDA-1997-1405"},{"key":"ref19","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref20","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02408"},{"key":"ref22","first-page":"54015","article-title":"Q-align: Teaching lmms for visual scoring via discrete text-defined levels","volume-title":"Int. Conf. Mach. Learn","author":"Wu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00641"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01350"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"}],"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\/11492212.pdf?arnumber=11492212","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:29:02Z","timestamp":1778048942000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492212\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00338","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}