Mengyu Ye

I am currently a 2nd year Ph.D. student in NLP at Fundamental AI lab (member of Tohoku NLP Group), Tohoku University, advised by Prof. Jun Suzuki.

My research interests lie in Natural Language Processing (NLP) and Machine Learning (ML). My previous work has focused on the interpretability of large language models (LLMs), driven by the goal of developing neural systems that are fully controllable and mechanistically understandable through a deep analysis of the algorithms they have learned.

More recently, my research has expanded to diffusion language models, where I explore the combination of post-training methods and tailored inference-time algorithms to enhance their performance. In parallel, I have also been working on building agent systems capable of operating effectively under real-world conditions.