Homepage

Hello and வணக்கம் 👋! I am Prashant Govindarajan, a third year Computer Engineering PhD student at Mila-Quebec AI Institute and Polytechnique Montréal (engineering school of UdéM), working under Sarath Chandar. I am keenly interested in AI for scientific discovery focusing on drug and material design. I am primarily exploring reinforcement learning and geometric deep learning approaches. My current project, which is in collaboration with Intel, is on developing offline reinforcement learning methods for crystalline material design using first-principles. I am also working on a project with Ansys on LLMs for 3D object generation, focusing on Computer-Aided Design (CAD). I was previously a dual degree student at the Indian Institute of Technology Madras, where I worked under Balaraman Ravindran and Karthik Raman on target-specific drug design.

Besides academics, I like playing football and frisbee, reading, and cooking. Feel free to reach out to me if you wish to have a chat about research and beyond 😁! Also, I am always looking forward to strengthening my foundations in crystallography, density functional theory, and solid-state physics, and getting domain-related inputs for my research. So if you have a background in these areas or wish to discuss about the RL aspects of my research, I’d love to have a conversation some time!

Publications

  • Govindarajan, Prashant, Mathieu Reymond, Santiago Miret, Antoine Clavaud, Mariano Phielipp, and Sarath Chandar. A Reinforcement Learning Pipeline for Band Gap-directed Crystal Generation. In AI for Accelerated Materials Design-Vienna 2024.
  • Govindarajan, Prashant, Santiago Miret, Jarrid Rector-Brooks, Mariano Phielipp, Janarthanan Rajendran, and Sarath Chandar. Learning Conditional Policies for Crystal Design Using Offline Reinforcement Learning. Digital Discovery (2024).
  • Govindarajan, Prashant, Santiago Miret, Jarrid Rector-Brooks, Mariano Phielipp, Janarthanan Rajendran, and Sarath Chandar. Behavioral Cloning for Crystal Design.” In Workshop on Machine Learning for Materials, ICLR 2023.

News