activity
20222026
most citedDynamic Data Augmentation via MCTS for Prostate MRI Segmentation

4 citations · 7 across the 5 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.CV2026

D-Scope: Decomposing and Steering Diffusion Transformers with Sparse Autoencoders

Xinyue Xu, Jiahao Zhang, Lijie Hu +2

Sparse autoencoders (SAEs) reveal visual structure in diffusion transformers (DiTs), but interpreting a feature does not establish whether it can be used to control generation. We…