Poster Fri, Sep 11, 2026 • 1:30 AM – 3:30 AM PDT ExHall # 51

Background Blurring Matters: Improving Visual Grounding by Merging Text-Irrelevant Tokens

Ruilin Yao ⋅ Shengwu Xiong ⋅ Shanshan Yang ⋅ Tianyu Zou ⋅ Shili Xiong ⋅ Yi Rong

Keywords: Vision Foundation Models: Interpretability and Reasoning