News › Computer science & data
Computer science & dataUCL: the "REM" AI model reconstructs entire particle collisions, efficiency 61% to 92% (in simulation)
UCL researchers built the Reconstruct Everything Model (REM), a unified machine-learning framework that reconstructs particles directly from measurements across all detector systems, replacing the traditional chain of specialised algorithms. On a detailed simulation of a detector proposed for CERN's Future Circular Collider, reconstruction efficiency rose from 61% to 92%, jet energy resolution improved by 52%, and a full collision is reconstructed in about 30 ms on a single GPU. These results are on simulated data, not real collider data.
Source: UCL
Need a custom AI tool?
Describe your need briefly; you will get clarifying questions and a scoped proposal before any work starts.
Related news
Computer science & data · 2026-11-03
NSF selects FabAID: a $24.5 million national data fabric for AI-driven science
Computer science & data · 2026-11-02
KAIST: CluSTER cuts LLM fine-tuning time by up to 69.6% with nearly the same quality
Computer systems & chips · 2026-11-04