Xin Chen

I am a Machine Learning Software Engineer at Intel, where I work on computer vision, deep learning, model finetuning, prompt optimizaiton, downstream tasks from foundation models and full stack model deployment, which includes pre-trained model optimization (Distillation and Pruning), model inference profiling and acceleration on GPU and CPU (both kernel-based and compiler-based methods) and safety and robustness evaluation of generative models.
Before joining Intel, I worked at many academic institutions and industry R&D teams.

Email  /  CV  /  Google Scholar  /  Github


News

Selected Publications [Google Scholar]

(*Equal Contribution, Corresponding Author)

Granted Patents

Honors & Awards

Professional Activities


© Xin Chen | Last updated: March 2024