Vision-G1: Towards General Reasoning Vision-Language Models via Reinforcement Learning
Zha, Yuheng Zhou, Kun Wu, Yujia Wang, Yushu Feng, Jie Xu, Zhi Hao, Shibo Liu, Zhengzhong Xing, Eric P Hu, Zhiting
Zha, Yuheng
Zhou, Kun
Wu, Yujia
Wang, Yushu
Feng, Jie
Xu, Zhi
Hao, Shibo
Liu, Zhengzhong
Xing, Eric P
Hu, Zhiting
Supervisor
Department
Machine Learning
Embargo End Date
Type
Conference proceeding
Date
License
Language
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Recent vision-language models (VLMs) show strong reasoning capabilities through training with reinforcement learning from verifiable rewards (RLVR). Despite their impressive capabilities, current VLMs focus on a limited range of reasoning tasks, such as mathematical and logical reasoning, due to the lack of readily available verifiable reward data in broader domains. As a result, these models struggle to generalize their reasoning abilities to the wide variety of challenges encountered in real-world environments. To address this limitation, we collect and assemble a comprehensive RL-ready visual reasoning training dataset encompassing 46 datasets across 13 dimensions of 5 domains, covering a wide range of realistic scenarios such as infographic reasoning, mathematical reasoning, spatial reasoning, and general science reasoning. Based on this dataset, we propose an influence function-based data filtering strategy and a multi-round data curriculum method to iteratively strengthen general visual reasoning abilities. Using this approach, we train a general reasoning VLM, namely Vision-G1. Our 7B model achieves state-of-the-art performance across nine visual reasoning benchmarks, surpassing previous similar-sized VLMs and even GPT-4o and Gemini-1.5 Flash.
Citation
Y. Zha, K. Zhou, Y. Wu, Y. Wang, J. Feng, Z. Xu , et al., "Vision-G1: Towards General Reasoning Vision-Language Models via Reinforcement Learning," 2026, pp. 28131-28139.
Source
Proceedings of the AAAI Conference on Artificial Intelligence
Conference
AAAI Conference on Artificial Intelligence
Keywords
46 Information and Computing Sciences, 4602 Artificial Intelligence, 4611 Machine Learning, 4 Quality Education
Subjects
Source
AAAI Conference on Artificial Intelligence
Publisher
Association for the Advancement of Artificial Intelligence