{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T21:26:58Z","timestamp":1781213218471,"version":"3.54.1"},"reference-count":75,"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\/100000185","name":"DARPA","doi-asserted-by":"publisher","award":["HR001124S0029-AIQ-FP-019"],"award-info":[{"award-number":["HR001124S0029-AIQ-FP-019"]}],"id":[{"id":"10.13039\/100000185","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\/iccv51701.2025.00117","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1173-1184","source":"Crossref","is-referenced-by-count":1,"title":["Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension"],"prefix":"10.1109","author":[{"given":"Xiyao","family":"Wang","sequence":"first","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengyuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linjie","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongjin","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuancheng","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chung-Ching","family":"Lin","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Lin","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Furong","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Learning to reason with llms","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"issue":"3","key":"ref4","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref5","article-title":"Large language monkeys: Scaling inference compute with repeated sampling","author":"Brown","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Transfer q star: Principled decoding for llm alignment","author":"Chakraborty","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00356"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"key":"ref10","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv preprint"},{"key":"ref11","author":"Chen","year":"2023","journal-title":"Mitigating hallucination in visual language models with visual supervision"},{"key":"ref12","first-page":"24185","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chen","year":"2024"},{"key":"ref13","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"ref17","author":"Hansen","year":"2022","journal-title":"Temporal difference learning for model predictive control"},{"key":"ref18","author":"Hosseini","year":"2024","journal-title":"Vstar: Training verifiers for self-taught reasoners"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01745"},{"key":"ref20","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021","journal-title":"arXiv preprint"},{"key":"ref21","author":"Jiang","year":"2024","journal-title":"Mantis: Interleaved multi-image instruction tuning"},{"key":"ref22","article-title":"Revisit large-scale imagecaption data in pre-training multimodal foundation models","author":"Lai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01316"},{"key":"ref25","author":"Li","year":"2024","journal-title":"Llava-onevision: Easy visual task transfer"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1561\/0600000110"},{"key":"ref27","author":"Li","year":"2024","journal-title":"Common 7b language models already possess strong math capabilities"},{"key":"ref28","author":"Li","year":"2024","journal-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models"},{"key":"ref29","article-title":"Let\u2019s verify step by step","author":"Lightman","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","author":"Lightman","year":"2023","journal-title":"Let\u2019s verify step by step"},{"key":"ref31","article-title":"Aligning large multi-modal model with robust instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref33","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref35","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","volume-title":"International Conference on Learning Representations (ICLR)","author":"Lu","year":"2024"},{"key":"ref36","article-title":"Gpt-4v(ision) system card","year":"2023","journal-title":"OpenAI"},{"key":"ref37","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref39","article-title":"Eagle: Exploring the design space for multimodal 11 ms with mixture of encoders","author":"Shi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref41","article-title":"Scaling 11 m test-time compute optimally can be more effective than scaling model parameters","author":"Snell","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","author":"Snell","year":"2024","journal-title":"Scaling 11 m test-time compute optimally can be more effective than scaling model parameters"},{"key":"ref43","author":"Sun","year":"2023","journal-title":"Aligning large multimodal models with factually augmented rlhf"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022633531479"},{"key":"ref45","article-title":"Gemini: A family of highly capable multimodal models","year":"2023","journal-title":"Google Gemini Team"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3274536"},{"key":"ref47","article-title":"Toward self-improvement of 11 ms via imagination, searching, and criticizing","author":"Tian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","author":"Tong","year":"2024","journal-title":"Cambrian-1: A fully open, vision-centric exploration of multimodal 11 ms"},{"key":"ref49","article-title":"Solving math word problems with process-and outcome-based feedback","author":"Uesato","year":"2022","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Litesearch: Efficacious tree search for 11m","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Git: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Evaluation and analysis of hallucination in large vision-language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","author":"Wang","year":"2024","journal-title":"Amber: An 11 m -free multidimensional benchmark for mllms hallucination evaluation"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-53302-0_3"},{"key":"ref55","author":"Wang","year":"2024","journal-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.510"},{"key":"ref57","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Coplanner: Plan to roll out conservatively but to explore optimistically for model-based rl","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Enhancing visuallanguage modality alignment in large vision language models via self-improvement","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Towards selfimprovement of 11 ms via mcts: Leveraging stepwise knowledge with curriculum preference learning","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.25"},{"key":"ref62","article-title":"Simvlm: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2022","journal-title":"ICLR"},{"key":"ref63","article-title":"Lotlip: Improving language-image pre-training for long text understanding","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"Genarm: Reward guided generation with autoregressive reward model for test-time alignment","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","author":"Xue","year":"2024","journal-title":"Longvila: Scaling long-context visual language models for long videos"},{"key":"ref66","author":"Yang","year":"2024","journal-title":"Qwen2.5math technical report: Toward mathematical expert model via self-improvement"},{"key":"ref67","article-title":"The dawn of 1mms: Preliminary explorations with gpt-4v (ision)","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref68","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref69","author":"Yu","year":"2023","journal-title":"Mm -vet: Evaluating large multimodal models for integrated capabilities"},{"key":"ref70","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref72","article-title":"Rest-mcts*: Llm self-training via process reward guided tree search","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/icme59968.2025.11209377"},{"key":"ref74","article-title":"Aligning modalities in vision large language models via preference fine-tuning","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref75","article-title":"Calibrated self-rewarding vision language models","author":"Zhou","year":"2024","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\/11444611.pdf?arnumber=11444611","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:02Z","timestamp":1777612022000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444611\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00117","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}