Skip to content
conftrace_
2025 ICML ICML 2025

Diff-MoE: Diffusion Transformer with Time-Aware and Space-Adaptive Experts

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Computer Vision

Authors

Kun Cheng, Xiao He, Lei Yu, Zhijun Tu, Mingrui Zhu, Nannan Wang, Xinbo Gao, Jie Hu

Topics

Deep Learning > Architectures > Transformers Deep Learning > Models > Diffusion Models Computer Vision > Generation > Image Generation

Keywords

generative modeling diffusion model feature recalibration spatial token mixture-of-experts timestep conditioning
Download PDF