Poster Fri, Sep 11, 2026 • 1:30 AM – 3:30 AM PDT ExHall # 22

Understanding Geometric Representations in Self-Supervised Vision Transformers via Subspace Intervention

Weichen Zhou ⋅ Yawen Zou ⋅ Chunzhi Gu ⋅ Ran Dong ⋅ Haoran Xie ⋅ Chao Zhang

Keywords: Vision Foundation Models: Interpretability and Reasoning