Conference Publications

1. MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank Compensators. [pdf]
   Beichen Huang*, Yueming Yuan*, Zelei Shao*, Minjia Zhang (*Equal contribution).
   MLSys ‘2025.
   
   

   
   

2. SPLAT: A framework for optimised GPU code-generation for SParse reguLar ATtention. [pdf]
   Ahan Gupta, Yueming Yuan, Devansh Jain, Yuhao Ge, David Aponte, Yanqi Zhou, Charith Mendis.
   OOPSLA ‘2025.