Yein Park

Hi! (or "Annyeonghaseyo!") I am a Ph.D. student in Computer Science at the University of Cambridge (CambridgeNLP), advised by Prof. Andreas Vlachos. I am also a Gates Cambridge Scholar (Class of 2026). Prior to this, I received an M.S. in Computer Science & Engineering from Korea University as a member of DMIS Lab, advised by Prof. Jaewoo Kang, and a B.S. in Linguistics and Computer Science from the same institution. I worked as a research intern at Aigen Science Inc. and Nara Information.

My research covers the broad field of natural language processing, with a primary focus on driving Post-Training innovations through Mechanistic Interpretability. I trace the internal computations of LLMs to design interpretable alignment techniques for Safety, Knowledge Editing, Unlearning, and Reasoning. Moving forward, I envision devising fine-grained post-training methods that resolve localized breakdowns without robustness trade-offs. Beyond general models, I also apply RAG and RL techniques, along with these alignment insights, to Medical and Molecular LMs.

As AI becomes part of everyday decisions, trust can no longer be an afterthought. Ultimately, I aim to unite evaluation, interpretability, and training to build AI that is not only more capable, but also reliable and genuinely useful in improving people's lives.