Ximing Lu

Ximing

I am a Ph.D. candidate at the University of Washington and a research staff at NVIDIA, advised by Professor Yejin Choi. Previously, I received my B.S. degree in Computer Science at University of Washington.

My broad research goal is to understand the boundaries of machine intelligence and bridge the capability gap between models and humans by exploring alternative paths beyond scaling, such as algorithmic innovations and knowledge enhancement. Over the past few years, I have focused on studying the capabilities and limits of language models, as well as developing learning and inference algorithms to unlock capabilities in smaller models, for example:

At NVIDIA, my work is centered around synthesizing pre/post-training data, developing alternative learning paradigms and model architectures to empower reasoning capabilities in frontier models.

Email: lux32 [at] cs.washington.edu

Links: [Google Scholar] [Twitter] [Github] [CV] [Research Statement]

Publications

Publications are listed in reverse chronological order. For a list of all publications, please check out my Google Scholar

Honors & Awards

Teaching Experience

  • (Winter, 2024) TA @ CSE 447/517 (Undergrad/Grad NLP) at University of Washington
  • (Winter, 2021)-TA @ CSE P517 (Professional NLP) at University of Washington