Minwoo (Josh) Kang

I’m a fifth-year PhD student in Computer Science at UC Berkeley, where I am part of Berkeley AI Research (BAIR) and the SLICE Lab.
My research is advised by Prof. John Canny and Prof. John Wawrzynek.

I am generally interested in topics on language modeling and natural language processing, with a focus on:

• post-training large language models for generation consistency and diversity
• LM-LM and LM-Human interaction in collaborative games (where exploration is a must)
• language models as approximations of human samples and applications toward simulation of human studies
• language models as agents of code generation, optimization, and design-space exploration (DSE)