{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T08:30:36Z","timestamp":1778661036459,"version":"3.51.4"},"reference-count":72,"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\/iccv51701.2025.00245","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2545-2555","source":"Crossref","is-referenced-by-count":2,"title":["VisRL: Intention-Driven Visual Perception via Reinforced Reasoning"],"prefix":"10.1109","author":[{"given":"Zhangquan","family":"Chen","sequence":"first","affiliation":[{"name":"Tsinghua University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xufang","family":"Luo","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.arabicnlp-1.21"},{"key":"ref2","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Deepseek 11m: Scaling open-source language models with longtermism","author":"Bi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00363"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Internlm2 technical report","author":"Cai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Plug-and-play grounding of reasoning in multimodal large language models","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref10","volume-title":"R1v: Reinforcing super generalization ability in vision-language models with less than $3","author":"Chen","year":"2025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0614"},{"key":"ref12","article-title":"Longlora: Efficient finetuning of long-context large language models","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"issue":"5","key":"ref13","volume":"3","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality, march 2023"},{"key":"ref14","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00847"},{"key":"ref16","article-title":"Kto: Model alignment as prospect theoretic optimization","author":"Ethayarajh","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"ref18","author":"Fu","year":"2024","journal-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models"},{"key":"ref19","article-title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"ref21","article-title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.09.116"},{"key":"ref23","author":"Ji","year":"2024","journal-title":"Align anything: Training all-modality models to follow instructions with language feedback"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3634737.3659433"},{"key":"ref25","first-page":"81461","article-title":"Lumen: Unleashing versatile visioncentric capabilities of large multimodal models","volume":"37","author":"Jiao","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref27","article-title":"Step-dpo: Step-wise preference optimization for long-chain reasoning of 11 ms","author":"Lai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Imagine while reasoning in space: Multimodal visualization-ofthought","author":"Li","year":"2025","journal-title":"arXiv preprint"},{"key":"ref29","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified visionlanguage understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref30","first-page":"19730","article-title":"Blip2: 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":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref35","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref37","article-title":"Spatialcot: Advancing spatial reasoning through coordinate alignment and chain-of-thought for embodied task planning","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00197"},{"key":"ref39","volume-title":"3.2: Revolutionizing edge ai and vision with open, customizable models","author":"Meta","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1364"},{"key":"ref42","author":"Radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"},{"issue":"8","key":"ref43","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref44","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":"ref45","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"ref48","author":"Shao","year":"2024","journal-title":"Visual cot: Unleashing chain-of-thought reasoning in multi-modal language models"},{"key":"ref49","volume-title":"Vlm-r1: A stable and generalizable r1-style large vision-language model","author":"Shen","year":"2025"},{"key":"ref50","article-title":"Paligemma 2: A family of versatile vlms for transfer","author":"Steiner","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01465"},{"key":"ref52","year":"2023","journal-title":"Internlm: A multilingual language model with progressively enhanced capabilities"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1247"},{"key":"ref54","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2688"},{"key":"ref58","article-title":"Segllm: Multi-round reasoning segmentation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-017-0058"},{"key":"ref60","first-page":"69925","article-title":"Visionllm v2: An end-to-end generalist multimodal large language model for hundreds of vision-language tasks","volume":"37","author":"Wu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01243"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2866"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00890"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02781"},{"key":"ref65","article-title":"Baichuan 2: Open large-scale language models","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref66","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"Yi: Open foundation models by 01. ai","author":"Young","year":"2024","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref69","article-title":"Eventhallusion: Diagnosing event hallucinations in video llms","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","volume-title":"Gpt4roi: Instruction tuning large language model on region-of-interest","author":"Zhang","year":"2024"},{"key":"ref71","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"}],"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\/11445942.pdf?arnumber=11445942","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:05:06Z","timestamp":1777611906000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445942\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00245","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}