Antonin Sulc

Antonin Sulc, Ph.D.

Embedding consciousness to electronics.

Lawrence Berkeley National Laboratory

Computer Vision AI for Physics Agentic Systems
Download CV

About

I am a Researcher at Lawrence Berkeley National Lab (LBNL) specializing in autonomous systems. Currently, my work focuses on developing intelligent algorithms for particle accelerator controls, bridging the gap between advanced AI and high-energy physics. Previously a Senior Data Scientist at the Helmholtz Association (DESY/XFEL), I pioneered the use of Large Language Models in scientific contexts, including the development of "PACuna" and "ChatQCD". I hold a Ph.D. in Computer Vision from the University of Konstanz and actively shape the field as a Program Chair of Various Conferences & Workshops.

Selected Publications

Modal Logical Neural Networks

Antonin Sulc

2024

Recent Work

Agentic AI for Multi-Stage Physics Experiments at a Large-Scale User Facility Particle Accelerator

T. Hellert, D. Bertwistle, S.C. Leemann, A. Sulc, M. Venturini

Physical Review Research

Osprey: A Scalable Framework for the Orchestration of Agentic Systems

Thorsten Hellert, Joao Montenegro, Antonin Sulc

AIP Conference Proceedings, 2024

Event2Vec: A Geometric Approach to Learning Composable Representations of Event Sequences

Antonin Sulc

Symmetry and Geometry in Neural Representations at NeurIPS, 2025

Agentic System with Modal Logic for Autonomous Diagnostics

Antonin Sulc, Thorsten Hellert

2024

Quantum Noise Tomography with Physics-Informed Neural Networks

Antonin Sulc

2024

Peer-Reviewed Publications

Agentic AI at the Advanced Light Source

Thorsten Hellert, João Montenegro, Antonin Sulc

ML4Physics Workshop at NeurIPS 2025, San Diego, CA

Towards Agentic AI on Particle Accelerators

A. Sulc, T. Hellert, R. Kammering, H. Houscher, J. M. St. John

ML4Physics Workshop at NeurIPS 2024, Vancouver, CA

PACuna: Automated Fine-Tuning of Language Models for Particle Accelerators

A. Sulc, R. Kammering, A. Eichler, T. Wilksen

ML4Physics Workshop at NeurIPS 2023, New Orleans, USA

Towards Monocular Shape from Refraction

A. Sulc, I. Sato, B. Goldluecke, T. Treibitz

BMVC 2021 (Oral, 3.3% acceptance)

Depth from Spectral Defocus Blur

S. Ishihara, A. Sulc, I. Sato

ICIP 2019

Journal Articles

Unsupervised Log Anomaly Detection with Few Unique Tokens

A. Sulc, A. Eichler, T. Wilksen

IET Journal Information Security, 2023

A Data-Driven Anomaly Detection on SRF Cavities at the European XFEL

A. Sulc, A. Eichler, T. Wilsken

Journal of Physics: Conference Series, Vol. 2420, No. 1, 2023

Recovery of Geometry, Natural Illumination and BRDF from a Single Light Field Image

A. Sulc, O. Johannsen, B. Goldluecke

Journal of the Optical Society of America A, 2022

Depth Estimation Using Spectrally Varying Defocus Blur

S. Ishihara, A. Sulc, I. Sato

Journal of the Optical Society of America A, 2021

Conference Proceedings

Unsupervised Anomaly Detection in ALS EPICS Event Logs

A. Sulc, T. Hellert, S. Hunt

ICALEPCS 2025

Toward Particle Accelerator Machine State Embeddings as a Modality for Large Language Models

F. Mayet, T. Hellert, A. Sulc, C. Tennant

ICALEPCS 2025

QCD in Language Models: What They Really Know About QCD?

A. Sulc, P. Connor

EPS-High Energy Physics 2025

eLog Analysis for Accelerators: Status and Future Outlook

A. Sulc, T. Hellert, A. Reed, A. Bien, C. Bisegni, D. Ratner, A. Carpenter, C. Tennant, D. Lersch, D. McSpadden, T. Britton, H. Hoschouer, J. St. John

IPAC 2025

ChatQCD: Let Large Language Models Explore QCD

A. Sulc, P. Connor

42nd International Conference on High Energy Physics (ICHEP 2024)

Automated Anomaly Detection on European XFEL Klystrons

A. Sulc, A. Eichler, T. Wilksen

IPAC 2024, Nashville, USA

Towards Unlocking Insights from Logbooks Using AI

A. Sulc, A. Eichler, G. Hartmann, T. Wilksen, J. St. John, F. Mayet, J. Maldonado, D. Ratner, J. Kaiser, V. Kain, T. Hellert, H. Hoschouer

IPAC 2024, Nashville, USA

Log Anomaly Detection on EuXFEL Nodes

A. Sulc, A. Eichler, T. Wilksen

ICALEPCS 2023, Cape Town, South Africa (Oral)

Invited Talks & Presentations

Generalizing LLMs for Accelerators with RL

A. Sulc

3rd International Workshop on Reinforcement Learning for Autonomous Accelerators (RL4AA'25), Hamburg, Germany

Addressing Challenges in Accelerator Operations with Artificial Intelligence

A. Sulc

Accelerator Seminar @ Jefferson Lab, USA