About
I am a researcher interested in foundation models, with a focus on the data and systems that make language models more capable, efficient, and reliable.
My current work spans post-training data, pre-training data laws, retrieval-augmented generation, and efficient language models. I am especially interested in turning empirical observations into practical methods that scale.
Selected updates
View CV
Joined Huawei 2012 Theory Lab as a researcher.
Joined Microsoft Research & Ads as an intern, working on information retrieval for ads and language models.