{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:04Z","timestamp":1777865344228,"version":"3.51.4"},"reference-count":66,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00138","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1402-1412","source":"Crossref","is-referenced-by-count":0,"title":["Improving Large Vision and Language Models by Learning from a Panel of Peers"],"prefix":"10.1109","author":[{"given":"Jefferson","family":"Hernandez","sequence":"first","affiliation":[{"name":"Rice University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Shi","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Jenni","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vicente","family":"Ordonez","sequence":"additional","affiliation":[{"name":"Rice University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kushal","family":"Kafle","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"The llama 3 herd of models","volume-title":"arXiv preprint","year":"2024"},{"key":"ref3","article-title":"Theoretical guarantees on the best-of-n alignment policy","author":"Beirami","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Are we on the right way for evaluating large visionlanguage models?","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Self-play fine-tuning converts weak language models to strong language models","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref7","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality"},{"key":"ref8","article-title":"Selfimproving robust preference optimization","author":"Choi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Reward model ensembles help mitigate overoptimization","volume-title":"The Twelfth International Conference on Learning Representations","author":"Coste","year":"2024"},{"key":"ref11","article-title":"Enhancing large vision language models with self-training on image comprehension","author":"Deng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685520"},{"key":"ref13","article-title":"vila2: Vila augmented vila","author":"Fang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models","author":"Guan","year":"2023","journal-title":"arxiv. 10.48550. arXiv preprint"},{"key":"ref15","article-title":"Mistral 7b (2023)","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.672"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref19","article-title":"Silkie: Preference distillation for large visual language models","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.765"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref23","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref24","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"Mmbench: Is your multi-modal model an all-around player?","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"On the hidden mystery of ocr in large multimodal models","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref28","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","volume-title":"The Twelfth International Conference on Learning Representations","author":"Lu","year":"2024"},{"key":"ref29","article-title":"Wildvision: Evaluating vision-language models in the wild with human preferences","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref31","article-title":"Simpo: Simple preference optimization with a reference-free reward","author":"Meng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.4324\/9781410603715"},{"key":"ref34","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"Ordonez","year":"2011","journal-title":"Advances in neural information processing systems, 24"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref37","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":"ref38","article-title":"Direct preference optimization: Your language model is secretly a reward model","author":"Rafailov","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref41","article-title":"Aligning large multimodal models with factually augmented rlhf","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Cambrian-1: A fully open, vision-centric exploration of multimodal 11 ms","author":"Tong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Replacing judges with juries: Evaluating llm generations with a panel of diverse models","author":"Verga","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"To see is to believe: Prompting gpt-4v for better visual instruction tuning","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Self-taught evaluators","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Enhancing visuallanguage modality alignment in large vision language models via self-improvement","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Helpsteer2: Open-source dataset for training top-performing reward models","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.185"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02098"},{"key":"ref51","article-title":"Self-play preference optimization for language model alignment","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"x.ai Team","volume-title":"Grok-1.5 vision preview","year":"2024"},{"key":"ref53","article-title":"Llavacritic: Learning to evaluate multimodal models","author":"Xiong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"The perfect blend: Redefining rlhf with mixture of judges","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01310"},{"key":"ref56","article-title":"Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Mm-vet: Evaluating large multimodal models for integrated capabilities","volume-title":"Forty-first International Conference on Machine Learning","author":"Yu","year":"2024"},{"key":"ref58","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Self-rewarding language models","author":"Yuan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref62","article-title":"Svit: Scaling up visual instruction tuning","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref63","article-title":"Aligning modalities in vision large language models via preference fine-tuning","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"Calibrated self-rewarding vision language models","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Selfsupervised visual preference alignment","author":"Zhu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref66","article-title":"Fine-tuning language models from human preferences","author":"Ziegler","journal-title":"arXiv preprint"}],"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\/11444796.pdf?arnumber=11444796","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:17:43Z","timestamp":1777529863000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444796\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00138","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}