Principal Scientist, Lila Sciences
Reinforcement Learning | Machine Learning | Decision Making Under Uncertainty
Currently, I am a Principal Scientist at Lila Sciences within the AI Research organization. We are enthusiastically focused on developing Scientific Superintelligence, bringing advanced AI into automated laboratory settings to accelerate scientific discovery, there's a lot of exciting things on the horizon!
I work in the fields of reinforcement learning, machine learning, and causal inference. I have long been interested in decision making and the mechanisms by which humans summarize and reason about the world. In my work, I aim to develop models and algorithms that enable actors (whether human or not) to efficiently make decisions in the face of various forms of uncertainty. Ultimately, my goal is to develop algorithmic techniques that extend beyond the domain in which they are trained, adapting to their end uses and any unique aspects/preferences therein.
I'm always keen on hearing about interesting ideas and love collaborating with others on a variety of problems, applied and foundational, as far as there is alignment with my areas of focus. Don't hesitate to reach out!
Current research projects and interests.
Overview Leading research efforts at MBZUAI’s Institute of Foundation Models to develop practical RL techniques for improving language model reasoning and alignment. Our work spans multiple reasoning domains through the...
Learn MoreOverview Developing risk-sensitive methods for identifying dangerous states and treatments in healthcare settings. Focus on dead-end identification using distributional RL and conservative value estimation for improved patient safety. Motivation In...
Learn MoreCourses, mentorship, and educational activities.
Course Overview A comprehensive introduction to machine learning for undergraduate students covering supervised learning, unsupervised learning, and practical ML skills. The course emphasizes both theoretical understanding and hands-on implementation of...
Learn MoreCourse Overview An introductory course designed for advanced undergraduates and beginning graduate students covering the fundamentals of reinforcement learning. Students will learn core concepts, implement basic algorithms, and understand when...
Learn MoreCourse Overview Graduate-level course covering modern RL techniques including offline RL, safe RL, and applications to real-world problems. Emphasis on bridging theory and practice with hands-on projects. Course Description This...
Learn MoreOverview Actively mentoring PhD students at MBZUAI on projects spanning RL for LLMs, safe decision-making, and practical applications of machine learning. Focus on developing both technical skills and research independence....
Learn MoreI'm working on sharing insights from my research and experiences in reinforcement learning, machine learning, and more.
As reinforcement learning (RL) continues to mature from a primarily theoretical discipline into one with increasingly tangible real-world applications, we find ourselves at a critical juncture. The same techniques that...
Read More