Aditya Grover is an assistant professor of computer science at UCLA. His goal is to develop intelligent agents that can interact and reason with limited supervision in the real world. This mission spans fundamental advances in deep unsupervised learning and interactive decision making and real-world grounding in applications focussing on climate science and technology. Aditya’s recent honors include a best paper award at NeurIPS, the ACM SIGKDD Doctoral Dissertation Award, the Forbes 30 Under 30 Honoree, the AI Researcher of the Year Award by Samsung, and the Kavli Fellowship by the US National Academy of Sciences. Aditya received his postdoctoral training at UC Berkeley, PhD from Stanford, and bachelors from IIT Delhi, all in computer science.

AI2050 Project

Climate change has led to a rapid increase in the occurrence of extreme weather events globally, including floods, droughts, and wildfires. Current models for forecasting extreme events are limited by the inability to efficiently model spatiotemporal physics at finer spatial resolutions and long lead times. In his AI2050 project, Aditya Grover will develop a new uncertainty-aware foundation model for forecasting extreme weather events. This model will be pretrained on broad atmospheric datasets using unsupervised learning and fine-tuned to integrate complex domain knowledge using modern alignment techniques. Grover will validate his approach on challenging real-world weather datasets and open-source the research for broader use and accessibility.