Multimodal Large Language Model

Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning
Multimodal Large Language Models (MLLMs) excel in solving text-based mathematical problems, but they struggle with mathematical …
Wenwen Zhuang, Xin Huang, Xiantao Zhang, Jin Zeng
PDF Cite Code Dataset
Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning