2 papers
cs.CV2025
A Stepwise Distillation Learning Strategy for Non-differentiable Visual Programming Frameworks on Visual Reasoning Tasks
Wentao Wan, Nan Kang, Zeqing Wang +3
Recently, Visual Programming (VProg) has emerged as a significant framework for visual reasoning (VR) tasks due to its interpretability and cross-task generality. However, even wit…
cs.CV2025
Towards Top-Down Reasoning: An Explainable Multi-Agent Approach for Visual Question Answering
Zeqing Wang, Wentao Wan, Qiqing Lao +5
Recently, to comprehensively improve Vision Language Models (VLMs) for Visual Question Answering (VQA), several methods have been proposed to further reinforce the inference capabi…