AI RESEARCH
Reconfigurable Computing Challenge: Real-Time Graph Neural Networks for Online Event Selection in Big Science
arXiv CS.LG
•
ArXi:2605.10612v1 Announce Type: cross Graph neural networks are increasingly adopted in trigger systems for collider experiments, where strict latency and throughput constraints render deployment on embedded platforms challenging. As detectors move towards higher granularity, the number of inputs per inference increase and FPGA-only solutions face resource bottlenecks.