{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:31:56Z","timestamp":1777865516189,"version":"3.51.4"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006754","name":"Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-23-2-0007,W911QX-24-F-0049"],"award-info":[{"award-number":["W911NF-23-2-0007,W911QX-24-F-0049"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"DARPA","doi-asserted-by":"publisher","award":["FA8750-23-2-1015"],"award-info":[{"award-number":["FA8750-23-2-1015"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","award":["N00014-23-1-2840"],"award-info":[{"award-number":["N00014-23-1-2840"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01MH125740,R01MH132225,R21MH130767"],"award-info":[{"award-number":["R01MH125740,R01MH132225,R21MH130767"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00309","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3225-3234","source":"Crossref","is-referenced-by-count":0,"title":["ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Zifu","family":"Wan","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ce","family":"Zhang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Silong","family":"Yong","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin Q.","family":"Ma","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Stepputtis","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Louis-Philippe","family":"Morency","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deva","family":"Ramanan","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katia","family":"Sycara","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaqi","family":"Xie","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref2","article-title":"Hallucination of multimodal large language models: A survey","author":"Bai","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref3","article-title":"Detecting and evaluating medical hallucinations in large vision language models","author":"Chen","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"ref5","article-title":"Mitigating hallucination in visual language models with visual supervision","author":"Chen","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref6","first-page":"7824","article-title":"HALC: Object hallucination reduction via adaptive focal-contrast decoding","volume-title":"International Conference on Machine Learning","author":"Chen","year":"2024"},{"key":"ref7","volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref8","article-title":"Dola: Decoding by contrasting layers improves factuality in large language models","volume-title":"International Conference on Learning Representations","author":"Chuang","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01356"},{"key":"ref11","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02553"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref17","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning","author":"Li","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.687"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref23","volume-title":"Llava-next: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref24","article-title":"A survey on hallucination in large vision-language models","author":"Liu","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3902"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00914"},{"key":"ref33","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1179"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.937"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_10"},{"key":"ref37","first-page":"13040","article-title":"Mplug-owl2: Revolutionizing multi-modal large language model with modality collaboration","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ye","year":"2024"},{"key":"ref38","article-title":"Woodpecker: Hallucination correction for multimodal large language models","author":"Yin","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref39","article-title":"MM-vet: Evaluating large multimodal models for integrated capabilities","volume-title":"International Conference on Machine Learning","author":"Yu","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02214-4"},{"key":"ref41","article-title":"Incorporating generative feedback for mitigating hallucinations in large vision-language models","volume-title":"Workshop on Responsibly Building the Next Generation of Multimodal Foundational Models","author":"Zhang","year":"2024"},{"key":"ref42","article-title":"Vscan: Rethinking visual token reduction for efficient large vision-language models","author":"Zhang","year":"2025","journal-title":"arxiv preprint arxiv"},{"key":"ref43","article-title":"Selfcorrecting decoding with generative feedback for mitigating hallucinations in large vision-language models","volume-title":"International Conference on Learning Representations","author":"Zhang","year":"2025"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_12"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445104.pdf?arnumber=11445104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:45:11Z","timestamp":1777531511000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445104\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00309","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}