3 citations · 7 across the 10 of their papers we have counts for
5 papers · 1 filter
Compress to Remember: Learning Compact Memory via On-Policy Distillation for Long Video Generation
Xiaoyu Wu, Weihang Guo, Yifei Wang +3
Standard video generators do not natively compact historical context into reusable memory tokens. As generation continues, the growing history makes it increasingly difficult to re…
Representation by Design in Generation: Cross-View Class-Token Alignment in Diffusion Transformers
Xiaoyu Wu, Yifei Wang, Chen Wei
Generative and representation learning remain asymmetrically connected: semantic representations are used to improve diffusion generation, whereas the models' own representations a…
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…
Integrating Amortized Inference with Diffusion Models for Learning Clean Distribution from Corrupted Images
Yifei Wang, Weimin Bai, Weijian Luo +2
Diffusion models (DMs) have emerged as powerful generative models for solving inverse problems, offering a good approximation of prior distributions of real-world image data. Typic…
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…