activity
20232026
most citedCAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications

22 citations · 27 across the 5 of their papers we have counts for

collaborators
Showing stat.MLShow all

1 paper · 1 filter

stat.ML2026

Robust Diffusion Models via Divergence-Induced Weighted Denoising

Lei Li, Yuexiao Dong

We show that replacing the standard MSE denoising loss in diffusion models with a nonlinear transformation induced by an f-divergence yields a simple robust training surrogate that…