Weichen Zhou

ULIFLOW: Unified Latent Human-Object Interaction Flow

Text-conditioned 3D human--object interaction (HOI) generation remains challenging because individually plausible human and object motions do not necessarily form a coherent interaction. We argue...

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

Infant Hippocampal Segmentation in Ultra-Low-Field MRI Using External Datasets with Diverse Field Strengths

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

We introduce a controlled subspace intervention framework to investigate how self-supervised Vision Transformers (ViTs) encode dense geometric information. While linear probing is widely used to...