Skip to main content

NeurIPS 2025

Playing with Transformer at 30+ FPS via Next-Frame Diffusion
Xinle Cheng
Tianyu He†
Jiayi Xu
Junliang Guo
Di He
Jiang Bian
Arxiv NeurIPS 2025
In this work, we present Next-Frame Diffusion (NFD), an autoregressive diffusion transformer that incorporates block-wise causal attention, enabling iterative sampling and efficient inference via parallel token generation within each frame.