AIRES: AI for Rare Event Search
Research
Click here for selected publications
Nature
Encoder
Decoder
Self-Supervised Learning (SSL)
By training on large, unlabelled datasets, SSL models acquire a task-agnostic representation of detector data. Key for unlocking the "ChatGPT" of particle physics experiments.
Hardware-AI Codesign
Design and deploy cutting-edge machine learning models onto the next-generation data acquisition board, aiming at empower KamLAND-Zen with in-situ position reconstruction capabilities and real-time detector control functionality.
Reinforcement Learning
Using reinforcement learning to achieve weakly supervised classification of the energy spectrum or to control a robotic arm for detector characterization!
Physics Data Release for AI/ML
Releasing real neutrino and dark matter detector data to the public, allowing core AI algorithms to extract the signal and produce real physics results thereby advancing fundamental science!
GeM Group
The Germanium Machine Learning (GeM) Group within the LEGEND collaboration, leverages efficient and interpretable AI to aid all aspects of LEGEND analysis while educating domestic and international collaborators to gain AI experiences.
Physics
