Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Vision-G1: Towards General Vision Language Reasoning with Multi-Domain Data Curation

About

Despite their success, current training pipelines for reasoning VLMs focus on a limited range of tasks, such as mathematical and logical reasoning. As a result, these models face difficulties in generalizing their reasoning capabilities to a wide range of domains, primarily due to the scarcity of readily available and verifiable reward data beyond these narrowly defined areas. Moreover, integrating data from multiple domains is challenging, as the compatibility between domain-specific datasets remains uncertain. To address these limitations, we build a comprehensive RL-ready visual reasoning dataset from 46 data sources across 8 dimensions, covering a wide range of tasks such as infographic, mathematical, spatial, cross-image, graphic user interface, medical, common sense and general science. We propose an influence function based data selection and difficulty based filtering strategy to identify high-quality training samples from this dataset. Subsequently, we train the VLM, referred to as Vision-G1, using multi-round RL with a data curriculum to iteratively improve its visual reasoning capabilities. Our model achieves state-of-the-art performance across various visual reasoning benchmarks, outperforming similar-sized VLMs and even proprietary models like GPT-4o and Gemini-1.5 Flash. The model, code and dataset are publicly available at https://github.com/yuh-zha/Vision-G1.

Yuheng Zha, Kun Zhou, Yujia Wu, Yushu Wang, Jie Feng, Zhi Xu, Shibo Hao, Zhengzhong Liu, Eric P. Xing, Zhiting Hu• 2025

Related benchmarks

TaskDatasetResultRank
Multimodal UnderstandingMMMU
Accuracy53.4
437
Visual Question AnsweringChartQA
Accuracy85.6
371
Visual Question AnsweringAI2D
Accuracy82.1
249
Mathematical Multimodal ReasoningMathVista
Accuracy76.1
218
Multimodal Math ReasoningMathVision
Accuracy31.3
183
Multimodal Math ReasoningWeMath
Accuracy45.1
168
Multimodal ReasoningMMStar
Accuracy66
143
Visual Question AnsweringMMBench (MMB)
Accuracy88
76
Mathematical Visual Question AnsweringMathVista
Accuracy76.1
47
Visual Question AnsweringMMMU
Accuracy53.4
37
Showing 10 of 17 rows

Other info

Follow for update