Team members
Shubham Gandhi - Team leader
Graduate student at the Language Technologies Institute, Carnegie Mellon University, advised by Prof. Carolyn Rosé. Research focuses on reliable and efficient LLM agents for code, spanning process supervision, tool use control, and model collaboration for repository-level software engineering tasks.
Nachiket Kotalwar - Team leader
PhD student in Language Technologies at Carnegie Mellon University. Research focuses on personalized alignment and human-AI collaboration, with emphasis on coding assistants and educational tools.
André Duarte
Second-year PhD student in Language Technologies at Carnegie Mellon University and Instituto Superior Técnico. Research focuses on memorization in large language models, with emphasis on copyrighted data detection. Currently exploring agent safety as an extension of this work.
Aditya Oke
Graduate student in Language Technologies Institute at Carnegie Mellon University. Research interests: LLM Safety and building safer Coding Agents. Previously worked as senior software engineer at JPMorgan Chase.
Zhen Wu
PhD student at the Language Technologies Institute at Carnegie Mellon University. Research centers on understanding model representations and developing principled methods to steer behavior toward improved reasoning, alignment, and interpretability.
Rui Melo
PhD student at S3D at CMU and Faculty of Engineering at University of Porto, researching the intersection of Machine Learning and Software Engineering. Holds MSc from IST; previously AI Engineer at U.S. legal-tech startup. Research investigates methods to enhance trustworthiness of LLM-powered tools in software engineering, particularly through agentic workflows.
Atharva Naik
Second-year PhD student at the Language Technologies Institute, Carnegie Mellon University, advised by Carolyn Rosé. Research on synthetic data and post-training methods for improving LLM code quality, reasoning, and safety. Work spans MetaLint, PBEBench, CRScore, and secure code generation.
Abhav Mehrotra
Graduate student in the Language Technologies Institute, Carnegie Mellon University, advised by Daniel Fried. Research interests: LLM applications, specifically AI for Code. Worked with GitHub and Microsoft Research to build Copilot Workspace; published papers on repository-level coding including MASAI and CodeResearcher.
Kexun Zhang
Second-year PhD student at the Language Technologies Institute, Carnegie Mellon University, advised by Lei Li. Research interests: coding agents.
Danqing Wang
Third-year PhD student at the Language Technologies Institute, Carnegie Mellon University, advised by Lei Li. Research interests: reasoning and planning with LLM-based agents, including coding agents and multi-agent collaboration.
Weichen Yu
Second-year PhD student at Carnegie Mellon University in Electrical and Computer Engineering, advised by Matt Fredrikson. Previously master's student at Institute of Automation, Chinese Academy of Sciences. Research interests: robustness, attacks, and defenses in LLMs and multimodal generative models.
Faculty advisors
Carolyn Rosé
Kavcic-Moura Professor of Language Technologies and Human-Computer Interaction at CMU and Program Director for Masters of Computational Data Science Program. Research group's interdisciplinary and award-winning work represented in top venues of Language Technologies, Learning Sciences, Educational Technology, and Human-Computer Interaction.
Lei Li
Associate Professor in the Language Technologies Institute at Carnegie Mellon University. Works on generative AI for language and science, including multilingual NLP, machine translation (text, speech), security of large language models, agentic LLM, and AI for drug discovery and protein design.
