I am a second-year Computer Science Ph.D. student at Duke NLP, advised by Bhuwan Dhingra. My research focuses on developing efficient algorithms for language modeling. I am currently exploring reinforcement learning methods to improve the reasoning efficiency of LLMs, especially for complex tasks that involve long sequences.

My research is supported by the NSF Graduate Research Fellowship. Before Duke, I worked closely with Antonios Anastasopoulos on low-resource NLP.

Selected Publications