Rajit Rajpal

I am currently a PhD student at the University of Edinburgh in the MAC-MIGS programme funded by the Probabilistic AI Hub. My interests lie in generative modeling and optimization.

Supervised by Benedict Leimkuhler and Nikolay Malkin.

Email / Github / LinkedIn / Google Scholar

Projects
	Depth Guided Diffusion World Models (2025) Coming soon!
	Nonlinear Damping in Neural Network Training (2025) Coming soon!
	Adaptive Stepsizing for Stochastic Gradient Langevin Dynamics in Bayesian Neural Networks Rajit Rajpal, Benedict Leimkuhler, Yuanhao Jiang AAAI Workshop @ Math4AI (Oral, Top 10%), (2025) pdf / code
	Frugal Zero-Shot Diffusion-Based Image Restoration (2024) Rajit Rajpal, Marcos Obando, Dolly Chen, Bernardin Amogou Runner-up @ Diffusion Models PhD Hackathon (2024) poster / code
	Does Translation Invariance Improve Tractable Generative Models? Rajit Rajpal, Antonio Vergari MSc Dissertation; Poster at BayesAI Workshop (2024) pdf / code

Teaching

I have been a teaching assistant for:

Education

	University of California, Berkeley Aug 2019 – May 2022 B.A. Data Science
	University of Edinburgh Aug 2023 – Aug 2028 MSc/PhD in Applied Mathematics

Experience

	NASA Ames Research Center – Rhombus Power Mar 2022 – Mar 2023 Data Scientist
	Qubit Analytics May – Dec 2025 Research Scientist, Video Generation

Cloned from here!
Last updated: Nov 18, 2025