Zhou, Xun
19 publications
ICML
2025
Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts
ICLR
2025
FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
NeurIPS
2025
UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces