Rajit Rajpal

I am currently a PhD student at the University of Edinburgh in the MAC-MIGS programme funded by the ProbAI Hub and supervised by Benedict Leimkuhler and Esmeralda S. Whitammer. I am also a Founding Research Scientist at Overworld building Diffusion World Models.

Projects
	Waypoint 1.5: A Real Time Video World Model for Consumer Hardware Rajit Rajpal, Shahbuland Matiana, Liew Wei Pyn, Anmol Agarwal, Ryan Craig, Andrew Lapp, Mithun Hunsur, Sami BuGhanem, Scottie Fox, Aaron Sanders, Carson Poole, Irene Park, Dave Rossi, Spencer Frazier, Louis Castricato pdf / project page / huggingface
	Adaptive Momentum and Nonlinear Damping in Neural Network Training Katerina Karoni, Rajit Rajpal, Benedict Leimkuhler, Gabriel Stoltz ICML 2026 pdf / code
	Decoupling Appearance and Geometry in Diffusion World Models Rajit Rajpal, Tadgh Kelly, Maxime Vandegar 2025 code
	Adaptive Stepsizing for Stochastic Gradient Langevin Dynamics in Bayesian Neural Networks Rajit Rajpal, Benedict Leimkuhler, Yuanhao Jiang AAAI 2025 Workshop @ Math4AI (Oral, Top 10%) pdf / code
	Frugal Zero-Shot Diffusion-Based Image Restoration 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 @ BayesAI Workshop (2024) pdf / code

Teaching

I have been a teaching assistant for:

Education

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

Experience

	Overworld AI Jan 2026 - Present Founding Research Scientist
	Lit8 Apr – Dec 2025 Research Scientist, Video Generation
	Rhombus Power – NASA Ames Research Center Mar 2022 – Mar 2023 Data Scientist

Cloned from here!
Last updated: Nov 18, 2025