CERN and Mistral AI have signed a statement of intent to establish a long-term strategic partnership to develop foundation models for scientific discovery, the two organisations announced on Thursday.
At the centre of the partnership is a single pretrained Large Physics Model, called Flare, described as the first foundation model for collider physics. It will be trained on billions of simulated proton-proton collisions at CERN's Large Hadron Collider (LHC) and designed to support multiple tasks, from reconstructing particle collisions and identifying particles to flagging unexpected signals and evaluating future detector designs.
CERN holds around one exabyte — one million terabytes — of experimental data from the LHC. The number of collisions is set to increase tenfold with the HL-LHC upgrade, which is expected to begin operation around 2030.
CERN's Chief Information Officer Enrica Porcari said the partnership would advance AI capabilities that can serve the whole physics community and be shared. Mistral's Vice-President of AI for Engineering Johannes Brandstetter said the two sides had the opportunity to push the frontiers of high-energy physics.
No timeline or budget was disclosed. Both sides said the models could later serve other sciences beyond high-energy physics.