AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization

Yi Yang, Xiaoxuan He, Hongkun Pan, Xiyan Jiang, Yan Deng, Xingtao Yang, Haoyu Lu, Dacheng Yin, Fengyun Rao, Minfeng Zhu, Bo Zhang, Wei Chen

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning · 385 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add SFT on R1-Onevision data (ablation)Qwen2.5-VL-7B · MathVisionaccuracy: 25.4 -> 26.3Improved
add SFT on R1-Onevision data (ablation)Qwen2.5-VL-7B · MathVerse (ALL)accuracy: 43.6 -> 43.4No clear effect
add SFT on R1-Onevision data (ablation)Qwen2.5-VL-7B · MathVerse (Vision Only)accuracy: 38.2 -> 39.7Improved
add RL after SFT (ablation)R1-Onevision-7B · MathVisionaccuracy: 26.3 -> 29.9Improved
add RL after SFT (ablation)R1-Onevision-7B · MathVerse (ALL)accuracy: 43.4 -> 46.4Improved
add RL after SFT (ablation)R1-Onevision-7B · MathVerse (Vision Only)accuracy: 39.7 -> 40.0Improved
add SFT stage before RL (ablation)R1-Onevision-7B · MathVisionaccuracy: 28.0 -> 29.9Improved
apply SFT+RL pipeline to 3B baseQwen2.5-VL-3B · MathVisionaccuracy: 21.7 -> 23.7Improved
apply SFT+RL pipeline to 3B baseQwen2.5-VL-3B · MathVerse (ALL)accuracy: 34.7 -> 38.6Improved
apply SFT+RL pipeline to 3B baseQwen2.5-VL-3B · MathVerse (Vision Only)accuracy: 31.2 -> 35.5Improved
scale base model from 7B to 72BQwen2.5-VL · R1-Onevision-Bench (avg)accuracy: 32.1 -> 52.0Improved
apply R1-Onevision training to 7B baseQwen2.5-VL-7B · R1-Onevision-Bench (avg)accuracy: 32.1 -> 36.2Improved

Later papers that compared with this method

12 later accepted papers report R1-Onevision-7B as a baseline in their results tables; 9 of them report a better number on most of the results they share with it.

4 more not listed.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy