Associate Professor, University of Illinois, Urbana Champaign
4 papers at NeurIPS 2025
The generalization of a DiT is influenced by the inductive bias of attention locality rather than harmonic bases like UNet. Using attention window restrictions can modify its generalization ability.
REN extracts object-centric region tokens from frozen vision features using point prompts—no segmentation needed. It’s 60× faster and 35× lighter than SAM, with strong performance across tasks.