I’m Yueming Yuan (袁悦茗), a founding Member of Technical Staff at RadixArk.
At RadixArk, I build Miles, an open-source RL framework, and the RL support in SGLang.
Before joining RadixArk, I was a PhD student at UIUC, advised by Minjia Zhang, working on ML systems for training and inference.
I’m broadly interested in building the future of AI.
- Member of Technical Staff, RadixArk
Leading the development of Miles, an open-source framework for RL post-training of frontier models.
Miles repo · Miles v0.1 release · Miles v0.1 technical report
- University of Illinois Urbana-Champaign
PhD student, Computer Science, advised by Minjia Zhang. ML systems for training and inference. Dropped out.
- Zhejiang University
B.E., Computer Engineering.
- Miles v0.1: Production-Level Post-Training
Tom Chen, Mao Cheng, Shi Dong, Kangrui Du, Yanbin Jiang, Jiajun Li, Yiming Li, Tao Lin, Yusheng Su, Andy Ye, Yueming Yuan, Zhichen Zeng. Technical report.
- X-MoE: Enabling Scalable Training for Emerging Mixture-of-Experts Architectures on HPC Platforms
Yueming Yuan, Ahan Gupta, Jianping Li, Sajal Dash, Feiyi Wang, Minjia Zhang.
- MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank Compensators
Beichen Huang*, Yueming Yuan*, Zelei Shao*, Minjia Zhang. *Equal contribution.
- SPLAT: A Framework for Optimised GPU Code-Generation for SParse reguLar ATtention
Ahan Gupta, Yueming Yuan, Devansh Jain, Yuhao Ge, David Aponte, Yanqi Zhou, Charith Mendis.
- Miles: Enterprise-facing Agentic RL Framework
PyTorch Conference North America 2026.
- High-Performance LLM Serving and Training with SGLang
NVIDIA GTC 2026.