On-chip probabilistic inference for charged-particle tracking at the sensor edge
Abstract
Modern scientific instruments operate under increasingly extreme constraints on bandwidth, latency, and power. Inference at the sensor edge determines experimental data collection efficiency by deciding which information to save for further analysis. Particle tracking detectors at the Large Hadron Collider exemplify this challenge: pixelated silicon sensors generate rich spatiotemporal ionization patterns, yet most of this information is discarded due to data-rate limitations. Concurrently, advancements in co-design tools provide rapid turn-around for incorporating machine learning into application-specific integrated circuits, motivating designs for particle detectors with new integrated technologies. We demonstrate that neural networks embedded in the front-end electronics can infer charged-particle kinematic parameters from a single silicon layer. We regress hit positions and incident angles with calibrated uncertainties, while satisfying stringent constraints on numerical precision, latency, and silicon area. Our results establish a path toward probabilistic inference directly at the edge, opening new opportunities for intelligent sensing in high-rate scientific instruments.
Cite
@article{arxiv.2602.15946,
title = {On-chip probabilistic inference for charged-particle tracking at the sensor edge},
author = {Arghya Ranjan Das and David Jiang and Rachel Kovach-Fuentes and Shiqi Kuang and Ana Sofía Calle Muñoz and Danush Shekar and Jennet Dickinson and Giuseppe Di Guglielmo and Lindsey Gray and Mia Liu and Corrinne Mills and Mark S. Neubauer and Daniel Abadjiev and Anthony Badea and Doug Berry and Karri DiPetrillo and Farah Fahim and Abhijith Gandrakota and Harshul Gupta and James Hirschauer and Eliza Howard and Ron Lipton and Petar Maksimovic and Nick Manganelli and Benjamin Parpillon and Jannicke Pearkes and Ricardo Silvestre and Morris Swartz and Chinar Syal and Nhan Tran and Amit Trivedi and Keith Ulmer and Mohammad Abrar Wadud and Benjamin Weiss and Eric You},
journal= {arXiv preprint arXiv:2602.15946},
year = {2026}
}