Kang Chen

I am a second-year Ph.D. student advised by Prof. Yixin Cao. My research interests lie in the intrinsic interpretability of large language models, with a focus on understanding and improving their reasoning and agentic capabilities.

I am also interested in how increasingly capable reasoning models and AI agents may reshape human society. I feel fortunate to live in this era of extraordinary technological progress, and I hope to contribute to building AI systems that are more capable, interpretable, and beneficial.

Previously, I worked as an algorithm research intern at SenseTime, Baidu Wenxin, and Alibaba Taotian Group.

Feel free to reach out if you are interested in LLM reasoning, AI agents, interpretability, or the societal impact of AI.