TensorX
返回文献探索

Paper · arXiv 2407.08739

MAVIS: Mathematical Visual Instruction Tuning

Renrui Zhang, Xinyu Wei, Dongzhi Jiang, Yichi Zhang, Ziyu Guo, Chengzhuo Tong, Jiaming Liu, Aojun Zhou, Bin Wei, Shanghang Zhang, Peng Gao, Hongsheng Li

31 upvotesJuly 11, 2024arXiv 预印本
AI 摘要

The paper introduces MAVIS, a comprehensive framework for improving the visual mathematics problem-solving capabilities of multi-modal large language models through tailored datasets and specialized training stages.

multi-modal large language modelsmathematical problem-solvingvisual encodingdiagram-language alignmentmathematical reasoning skillsMAVISMAVIS-CaptionMAVIS-Instructcontrastive learningchain-of-thought rationales

Abstract

Multi-modal Large Language Models (MLLMs) have recently emerged as a significant focus in academia and industry. Despite their proficiency in general multi-modal scenarios, the mathematical problem-solving capabilities in visual contexts remain insufficiently explored. We identify three key areas within MLLMs that need to be improved: visual encoding of math diagrams, diagram-language alignment, and mathematical reasoning skills. This draws forth an urgent demand for large-scale, high-quality data and training pipelines in visual mathematics. In this paper, we propose MAVIS, the first MAthematical VISual instruction tuning paradigm for MLLMs, involving a series of mathematical visual datasets and specialized MLLMs. Targeting the three issues, MAVIS contains three progressive training stages from scratch. First, we curate MAVIS-Caption, consisting of 558K diagram-caption pairs, to fine-tune a math-specific vision encoder (CLIP-Math) through contrastive learning, tailored for improved diagram visual encoding. Second, we utilize MAVIS-Caption to align the CLIP-Math with a large language model (LLM) by a projection layer, enhancing vision-language alignment in mathematical domains. Third, we introduce MAVIS-Instruct, including 900K meticulously collected and annotated visual math problems, which is adopted to finally instruct-tune the MLLM for robust mathematical reasoning skills. In MAVIS-Instruct, we incorporate complete chain-of-thought (CoT) rationales for each problem, and minimize textual redundancy, thereby concentrating the model towards the visual elements. Data and Models are released at https://github.com/ZrrSkywalker/MAVIS

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号