About me

Currently I am doing something extremely exciting. Previously, I was a research intern at Microsoft Research Asia (MSRA), mentored by Dr. Li Dong and Dr. Furu Wei, where I worked on reward reasoning models. I was also fortunate to be hosted by Prof. Tuo Zhao at Georgia Institute of Technology (GaTech), where I worked on adaptive knowledge distillation for speculative decoders.

Interest

I like training models. My ultimate goal is to explore and push the upper limits of model capabilities, enabling them to take over human.

News 🎉

• AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders has been accepted to NeurIPS 2025 as a Spotlight (top 3.5%). pdf slides video
• Reward Reasoning Model has been accepted to NeurIPS 2025 as a Poster. pdf poster slides video

Honors 🏅

• Studied Go together with Xinghao Wang under the guidance of Yiyi Liu, and at age 9, achieved Amateur 5-dan (highest amateur rank)
• 2018–2021: First Prize in the National High School Mathematics League (four consecutive years)