activity
20242026
collaborators

6 papers

cs.CV2026

An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations

Weimin Bai, Yifei Wang, Wenzheng Chen +1

Diffusion models excel in solving imaging inverse problems due to their ability to model complex image priors. However, their reliance on large, clean datasets for training limits…

cs.CV2026

Taming Outlier Tokens in Diffusion Transformers

Xiaoyu Wu, Yifei Wang, Tsu-Jui Fu +3

We study outlier tokens in Diffusion Transformers (DiTs) for image generation. Prior work has shown that Vision Transformers (ViTs) can produce a small number of high-norm tokens t…

cs.LG2026

Masked Auto-Regressive Variational Acceleration: Fast Inference Makes Practical Reinforcement Learning

Yuxuan Gu, Weimin Bai, Yifei Wang +2

Masked auto-regressive diffusion models (MAR) benefit from the expressive modeling ability of diffusion models and the flexibility of masked auto-regressive ordering. However, vani…

cs.NE2026

Biologically Plausible Learning via Bidirectional Spike-Based Distillation

Changze Lv, Yifei Wang, Yanxun Zhang +7

Developing biologically plausible learning algorithms that can achieve performance comparable to error backpropagation remains a longstanding challenge. Existing approaches often c…

cs.LG2025

Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instruction

Yifei Wang, Weimin Bai, Colin Zhang +3

In this paper, we unify more than 10 existing one-step diffusion distillation approaches, such as Diff-Instruct, DMD, SIM, SiD, -distill, etc, inside a theory-driven framework w…

cs.LG2024

Synergistic Development of Perovskite Memristors and Algorithms for Robust Analog Computing

Nanyang Ye, Qiao Sun, Yifei Wang +10

Analog computing using non-volatile memristors has emerged as a promising solution for energy-efficient deep learning. New materials, like perovskites-based memristors are recently…