{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T11:09:12Z","timestamp":1783076952046,"version":"3.54.6"},"reference-count":56,"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\/501100001475","name":"NTU Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001475","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\/iccv51701.2025.00181","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1859-1869","source":"Crossref","is-referenced-by-count":9,"title":["R1-VL: Learning to Reason with Multimodal Large Language Models via Step-Wise Group Relative Policy Optimization"],"prefix":"10.1109","author":[{"given":"Jingyi","family":"Zhang","sequence":"first","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxing","family":"Huang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huanjin","family":"Yao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shunyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xikun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shijian","family":"Lu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Anthropic","year":"2024","journal-title":"Claude 3.5 sonnet"},{"key":"ref2","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref3","article-title":"Training a helpful and harmless assistant with reinforcement learning from human feedback","author":"Bai","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref4","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":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.463"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"key":"ref7","article-title":"Self-play fine-tuning converts weak language models to strong language models","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref9","article-title":"Videollama 2: Advancing spatialtemporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00847"},{"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\/cvpr52733.2024.01363"},{"key":"ref13","article-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref14","article-title":"Vision-r1: Incentivizing reasoning capability in multimodal large language models","author":"Huang","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref15","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref17","article-title":"Gem: Empowering mllm for grounded ecg understanding with time series and images","author":"Lan","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref18","article-title":"Building and better understanding visionlanguage models: insights and future directions","volume-title":"Workshop on Responsibly Building the Next Generation of Multimodal Foundational Models","author":"Lauren\u00e7on","year":"2024"},{"key":"ref19","article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref20","volume-title":"Llava-next: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref21","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3653415"},{"key":"ref23","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","author":"Lu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref24","article-title":"Reft: Reasoning with reinforced fine-tuning","author":"Luong","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref25","article-title":"Macaw-llm: Multi-modal language modeling with image, audio, video, and text integration","author":"Lyu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref27","article-title":"Mm-eureka: Exploring the frontiers of multimodal reasoning with rule-based reinforce-ment learning","author":"Meng","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref28","article-title":"OpenAI","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref29","article-title":"OpenAI","year":"2024","journal-title":"Introducing openai o1"},{"key":"ref30","article-title":"Lmm-r1: Empowering 3b lmms with strong reasoning abilities through two-stage rule-based rl","author":"Peng","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref31","volume-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"ref33","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref34","article-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models","author":"Shao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref35","article-title":"video-salmonn: Speech-enhanced audio-visual large language models","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref36","article-title":"Kimi k1. 5: Scaling reinforcement learning with 11 ms","author":"Team","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref37","article-title":"Llamavo1: Rethinking step-by-step visual reasoning in 11 ms","author":"Thawakar","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref38","article-title":"Cambrian1: A fully open, vision-centric exploration of multimodal 11 ms","author":"Tong","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref39","volume-title":"Trl: Transformer reinforcement learning","author":"Von Werra","year":"2020"},{"key":"ref40","first-page":"95095","article-title":"Measuring multimodal mathematical reasoning with math-vision dataset","volume":"37","author":"Wang","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref42","article-title":"Next-gpt: Any-to-any multimodal 11 m","author":"Wu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"Deepseek-vl2: Mixture-ofexperts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref44","article-title":"Llava-o1: Let vision language models reason step-by-step","author":"Xu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00033"},{"key":"ref46","article-title":"Mulberry: Empowering mllm with o1-like reasoning and reflection via collective monte carlo tree search","author":"Yao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref47","article-title":"R1-sharevl: Incentivizing reasoning capability of multimodal large language models via share-grpo","author":"Yao","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref48","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref49","article-title":"mplug-docowl: Modularized multimodal large language model for document understanding","author":"Ye","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref50","article-title":"Rest-mcts*: Llm self-training via process reward guided tree search","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref51","article-title":"Mm1. 5: Methods, analysis & insights from multimodal 11 m fine-tuning","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_10"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.82"},{"key":"ref55","article-title":"Pmc-vqa: Visual instruction tuning for medical visual question answering","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref56","article-title":"Dynamath: A dynamic visual benchmark for evaluating mathematical reasoning robustness of vision language models","author":"Zou","year":"2024","journal-title":"arXiv preprint arXiv"}],"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\/11446203.pdf?arnumber=11446203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:21:45Z","timestamp":1777612905000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446203\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00181","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}