I’m a third year physics PhD student and AI researcher at Stanford University, interested in building intelligent systems that can understand and reason about sensor-level data from particle physics experiments.

I use tricks from computer vision and machine learning to train large neural networks to learn particle physics “by themselves” by looking at unlabeled data from particle detectors.

I am advised by Kazuhiro Terao in the neutrino group at SLAC National Accelerator Laboratory.

I’m most excited about self-supervised representation learning, 2D & 3D computer vision, and large-scale foundation models for the sciences. I’m happy to collaborate and interested to hear your ideas and feedback on the below works. Feel free to send me an email.

Selected research

  1. Panda Diplomacy: Foundation model pre-training across particle imaging detectors for high energy and nuclear physics

    Samuel Young, CĂ©sar JesĂşs-Valls, Kazuhiro Terao

    Anna Atkins cyanotype of five branching algae specimens.

    arXiv preprint, 2026

    Paper Code

    We show that the same model architecture and self-supervised learning recipe can learn useful particle physics without any labels across three radically different particle detectors (LArTPC, collider TPC, and water Cherenkov). With 1,000 labeled images Panda V2 acheives or gets close to SOTA performance on a variety of downstream tasks.

  2. Panda: Self-distillation of reusable sensor-level representations for high energy physics

    Samuel Young, Kazuhiro Terao

    Anna Atkins cyanotype of overlapping translucent kelp.

    arXiv preprint, 2025

    Project Paper Code

    We successfuly apply DINO-like self-distillation to unlabeled 3D images of particle interactions in a LArTPC. We show the model learns to cleanly separate particles and interaction types in latent space, which reduced the number of labeled images required to reach the state-of-the-art for semantic segmentation by 1,000x.

  3. 10 Million Particle Events: Enabling Foundation Models for Sparse 3D Inverse Problems

    Omar Alterkait, Sam Young, Ka Vang Tsang, Junjie Xia, Carolyn H Smith, Taritree Wongjirad, Kazuhiro Terao

    Anna Atkins cyanotype of long, looping ribbon-like algae.

    NeurIPS 2025 AI4Science Workshop (Spotlight)

    Paper

    We propose a new dataset containing 10 million images of particle interactions with realistic detector response and multiple modalities.

  4. Particle trajectory representation learning with masked point modeling

    Samuel Young, Yeon-jae Jwa, Kazuhiro Terao

    Anna Atkins cyanotype of three slender ribbon-like specimens.

    Machine Learning: Science and Technology, 2025

    Project Paper Code

    We propose a masked point modeling approach for learning representations of particle trajectories from unlabeled LArTPC images. PoLAr-MAE learns to separate tracks from showers almost perfectly without any labels.

News

  • Our group is co-leading a Genesis Mission project on combining Panda with symbolic models to accelerate scientific discovery for the DUNE experiment. Stanford Report

  • Panda was shown in two separate plenary talks at Neutrino 2026, the largest international conference for the field of neutrino physics.

  • Won the NPML poster awards for Insightful AI and Scientific Impact on my work applying Panda to two types of neutrino detectors.

  • I was awarded the HAI Graduate Fellowship.

  • Won Stanford’s CS 229 Machine Learning’s Best Project Award for my rotation work on pileup synthesis and anomaly detection for the ATLAS experiment.

  • I graduated from Penn with a bachelor’s and master’s in physics, and will continue my studies at Stanford.

  • I’m extremely grateful to receive the Roy and Diana Vagelos Challenge Award (two years full tuition and fees) at Penn.

Talks

  • NPML, “Toward a point cloud foundation model that learns physics across detection mechanisms” Slides

  • CHEP, “Toward a Foundation Model for Neutrino Physics: Self-distillation of Reusable Sensor-level Representations” Slides

  • HAI+SDS Annual Conference, “Learning the Structure of Particle Interactions From Raw Detector Data Without Labels” (Lightning Talk)

  • NPML, “Toward a general-purpose foundation model for neutrino physics” Slides

  • ML4FP Summer School, “Toward a general-purpose foundation model for neutrino physics” Slides

  • APS Global Summit, “A foundation model for LArTPC events”

  • APS April Meeting, “Differentiable surrogate for modeling the physics of optical propagation in a LArTPC”

  • 16th Marcel Grossmann Meeting, “The Optical Two- and Three-Dimensional Fundamental Plane Correlations for More than 130 Gamma-Ray Burst Afterglows”

  • APS April Meeting, “Impact of Spectral Photon Sorting in Large-Scale Neutrino Detectors”

  • APS Mid-Atlantic Section Annual Meeting, “Impact of Spectral Photon Sorting in Large-Scale Neutrino Detectors”

Artwork by Anna Atkins.