collaborators

5 papers

cs.CV2026

Self Gradient Forcing: Native Long Video Extrapolation

Junhao Zhuang, Shiyi Zhang, Yuxuan Bian +11

Recent autoregressive video diffusion methods are increasingly built upon Self Forcing, where the student is trained on histories produced by its own rollout rather than ground-tru…

cs.CV2026

Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions

Luxury, Jie Huang, Zihao Fan +25

While recent autoregressive video diffusion models achieve remarkable streaming quality, they remain confined to low resolutions (e.g., 480P), leaving efficient, scalable, real-tim…

cs.MM2026

Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation

Yuxuan Bian, Zeyue Xue, Songchun Zhang +9

We present Echo Infinity, an autoregressive (AR) framework towards real-time infinite video generation that employs a learnable evolving memory to dynamically filter, abstract, and…

cs.CV2024

Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning

Siyuan Li, Juanxi Tian, Zedong Wang +6

This paper delves into the interplay between vision backbones and optimizers, unvealing an inter-dependent phenomenon termed \textit{\textbf{b}ackbone-\textbf{o}ptimizer \textbf{c}…

cs.LG2024

Switch EMA: A Free Lunch for Better Flatness and Sharpness

Siyuan Li, Zicheng Liu, Juanxi Tian +9

Exponential Moving Average (EMA) is a widely used weight averaging (WA) regularization to learn flat optima for better generalizations without extra cost in deep neural network (DN…