arXiv cs.CV
· Papers
CURV: Enhancing Chart Understanding Through Curriculum Visual Grounded Reasoning
arXiv:2608.02833v1 Announce Type: new Abstract: Chart question answering (CQA) requires multimodal large language models (MLLMs) to integrate visual comprehension with logical reasoning, yet current models struggle with accurate visual grounding and coherent reasoning chains. While extrinsic chain-of-thought prompting