Pranav M. Murugan

I am a Staff Machine Learning Research Scientist at Genesis Molecular AI, working on novel generative AI methods for small-molecule drug discovery. I was a lead contributor for our foundation diffusion model, Pearl: check out the technical report here! I am generally interested in a range of problems, including hardware-aware design of model architectures (see e.g. PairMixer) and post-training (i.e. SFT, test-time scaling, RL) of diffusion models. Previously, I spearheaded Genesis’s efforts in building equivariant neural networks for state-of-the-art force fields for molecular simulation.

Prior to joining Genesis, I received my M.Eng. and S.B. from MIT with a double major in Physics and in Electrical Engineering and Computer Science. I primarily worked in the lab of Arup Chakraborty, where I studied computational models of the human immune system. I combined tools from statistical mechanics and information theory with massively parallel CUDA-accelerated stochastic simulation to design better vaccines and immunization protocols. Over the course of my undergraduate degree, I also worked as a machine learning research intern at Genesis Therapeutics, and in the labs of Mark Harnett (MIT) and Wesley Tansey (MSKCC). My work in these labs included deep learning classification of time-series neural signals and developing novel clustering-based methods for causal inference.

I was a member of the 2017 and 2018 US Physics Olympiad Team which was quite formative for my interest in physics; consider donating or getting involved if you’re interested!

In my free time, I dance and climb mountains with my friends.

Feel free to take a look around! I have a selected list of publications and projects in a wide range of topics highlighted in the respective sections. Currently, I’m best contacted at mpranav81 [at] gmail [dot] com.