Dr. Li "Harry" Zhang 张力

Assistant Professor

Dr. Zhang focuses on Natural Language Processing and Artificial Intelligence, with interests in planning and reasoning using Large Language Models.

Cassie Huang

PhD Student

Ceyhun Efe Kayan

PhD Student

Ceyhun focuses on applying mechanistic interpretability techniques to uncover reasoning patterns, provide robustness and improve planning and formalization performance of LLMs.

Prabhu Prakash Kagitha

MS Student

Rikhil Amonkar

UG Student

Stuti Mohan

UG Student

Chimezie Maduno

MS Intern

Chimezie is studying how to turn LLMs into modular, interpretable systems, where each component handles a specific reasoning skill. The goal is to design multi-agent pipelines that improve accuracy, robustness, and transparency in complex tasks.

Renxiang Wang

UG Intern

Renxiang is studying how to turn LLMs into modular, interpretable systems, where each component handles a specific reasoning skill. The goal is to design multi-agent pipelines that improve accuracy, robustness, and transparency in complex tasks.

Wenhao Hu

Intern

Muyu He

Intern → Collinear AI

Muyu He is working at collinear.ai as a research scientist focusing on post training and mechanistic interpretability. His research focus is primarily on efficient training paradigms and understanding attention-related latent space manifold transformations.

Liancheng Gong

Intern → PhD student at University of Maryland

Yuan Yuan

Intern, MS student at University of Pennsylvania

Yuan Yuan is a MS student in Computer and Information Science and Data Science at the University of Pennsylvania. He has experience in both NLP and multimodality, with research interests in reasoning, personalization, and LLM agents.