VisDoT : Enhancing Visual Reasoning through Human-Like Interpretation Grounding and Decomposition of Thought
VisDoT : 通过类人解释 grounding 和思维分解增强视觉推理
机构 * Department of Computer Science and Artificial Intelligence, Dongguk University(东国大学计算机科学与人工智能系) ; Department of Electronics and Electrical Engineering, Dongguk University(东国大学电子与电气工程系)
专题命中 视觉推理 :visual reasoning(title,abstract);grounding(title,abstract);vision-language model(abstract);InternVL(abstract)
AI总结 VisDoT 通过类人解释 grounding 和思维分解提升视觉推理,显著提升图表问答和开放领域视觉问答性能。
Comments 30 pages, 21 figures, EACL 2026 Findings