UC San Diego Secures DOE Genesis Mission Funding to Build Cutting‑Edge Scientific AI

In a move that could reshape how fundamental science is done, the University of California, San Diego has been awarded a grant from the Department of Energy’s new Genesis Mission. The money will fuel a team of physicists, data scientists and engineers who plan to build a sophisticated AI agent – whimsically named SIDERIUS – that can crunch data, design machine‑learning models and ship them onto custom chips for physics and quantum‑computing experiments.

The project is led by Aobo Li, an assistant professor of physics who also sits in the Halıcıoğlu Data Science Institute. “The next frontier of AI for science is learning how to translate scientific challenges into a form that AI can solve effectively,” Li says. Alongside her, associate professor Yi‑Zhuang You serves as co‑principal investigator; his start‑up, EdenCode, will help turn the AI ideas into working software.

SIDERIUS is envisioned as a large‑language‑model‑based scientist that can, for example, take raw detector data from a particle experiment, figure out which features matter, and then suggest a model that runs efficiently on a quantum‑ready processor. “Our long‑term vision is to build a general AI framework that can be adapted to many other data‑intensive scientific domains,” Li adds, hinting at applications that may someday stretch far beyond physics.

But the Genesis award isn’t the only piece of the puzzle. Li and several UC San Diego colleagues are co‑PIs on four additional projects that together span the globe. One partnership with the University of Colorado Boulder will create ultra‑fast AI tools to sift through the torrent of data generated by particle collisions at CERN’s Large Hadron Collider. Another collaboration with the University of North Carolina at Chapel Hill will deploy AI agents to speed up optical simulations for the LENGED experiment, which is hunting the ultra‑rare neutrinoless double‑beta decay that could explain why the universe favors matter over antimatter.

Further down the Pacific, UC San Diego physicists are joining forces with the University of Hawai‘i to assemble a unified foundation model built from AI‑ready datasets harvested from five different neutrinoless‑double‑beta‑decay experiments (CUORE, EXO‑200, Majorana Demonstrator, NEXT and SuperNEMO). And a final tie‑up with the Pacific Northwest National Laboratory aims to develop real‑time AI filters that protect LEGEND’s delicate detectors from background noise while preserving the precious signals of interest.

“AI is impacting scientific discovery in fundamental ways,” notes Rajesh K. Gupta, dean of the Halıcıoğlu School of Data Science and Computing. “Our interdisciplinary architecture—spanning physics, data science and supercomputing—is uniquely matched to the Genesis Mission. SIDERIUS will drive research in physics through new AI tools and methodologies that are bound to significantly advance our understanding of nature and invent new applications.”

In July, Li attended the Genesis Mission Summit in Washington, D.C., where she and her collaborators exchanged ideas with other awardees and DOE officials. The sheer number of Genesis projects involving UC San Diego underscores the campus’s deep bench of AI expertise and its growing role in shaping the future of scientific research.