Hi! I'm a fourth-year undergraduate at Princeton University, where I am incredibly fortunate to be advised by Prof. Karthik Narasimhan and Prof. Benjamin Eysenbach. I have also interned on Google Assistant's NLP team and was a resident at Redwood Research working on interpretability. Right now, I'm excited about:

• Robust unsupervised representation learning
• Interpreting and controlling models
• Frameworks for building reliable language agents

Other things I really like: tech policy, mechanism design, bioinformatics, all sorts of great writing, bouldering, BJJ, and cardistry. You can reach me at [x]@princeton.edu, where [x] is replaced by mwtang.

Papers