Skip to main content

About Me #

I am a doctoral researcher with a background in Computer Science and a passion for AI, currently completing my PhD at Deutsches Elektronen-Synchrotron DESY in Hamburg, Germany. My research focuses on the development of machine learning-based algorithms towards the goal of autonomous particle accelerator operations with a strong focus on control and tuning using reinforcement learning. My other research interests include surrogate modelling and virtual diagnostics using a variety of supervised learning methods.

Download my CV

Publications #

Jan Kaiser, Annika Eichler and Anne Lauscher. Large Language Models for Human-Machine Collaborative Particle Accelerator Tuning through Natural Language. In arXiv, 2024.

Sergey Tomin, Jan Kaiser, Nils Maris Lockmann, Torsten Wohlenberg and Igor Zagorodnov. Undulator Linear Taper Control at the European X-Ray Free-Electron Laser Facility. In Physical Review Accelerators and Beams, 2024.

Jan Kaiser, Chenran Xu, Annika Eichler and Andrea Santamaria Garica. Cheetah: Bridging the Gap Between Machine Learning and Particle Accelerator Physics with High-Speed, Differentiable Simulations. In arXiv, 2024.

Ryan Roussel, Auralee L. Edelen, Tobias Boltz, Dylan Kennedy, Zhe Zhang, Fuhao Ji, Xiaobiao Huang, Daniel Ratner, Andrea Santamaria Garcia, Chenran Xu, Jan Kaiser, Angel Ferran Pousa, Annika Eichler, Jannis O. Lübsen, Natalie M. Isenberg, Yuan Gao, Nikita Kuklev, Jose Martinez, Brahim Mustapha, Verena Kain, Weijian Lin, Simone Maria Liuzzo, Jason St. John, Matthew J. V. Streeter, Remi Lehe and Willie Neiswanger. Bayesian Optimization Algorithms for Accelerator Physics. In arXiv, 2023.

Jan Kaiser, Chenran Xu, Annika Eichler, Andrea Santamaria Garcia, Oliver Stein, Erik Bründermann, Willi Kuropka, Hannes Dinter, Frank Mayet, Thomas Vinatier, Florian Burkart and Holger Schlarb. Learning to Do or Learning While Doing: Reinforcement Learning and Bayesian Optimisation for Online Continuous Tuning. In arXiv, 2023.

Chenran Xu, Jan Kaiser, Erik Bründermann, Annika Eichler, Anke-Susanne Müller and Andrea Santamaria Garcia. Beam Trajectory Control with Lattice-agnostic Reinforcement Learning. In 14th International Particle Accelerator Conference (IPAC), 2023.

Jan Kaiser, Annika Eichler, Sergey Tomin and Zihan Zhu. Machine Learning for Combined Scalar and Spectral Longitudinal Phase Space Reconstruction. In 14th International Particle Accelerator Conference (IPAC), 2023.

Zihan Zhu, Sergey Tomin and Jan Kaiser. Application of Machine Learning in Longitudinal Phase Space Prediction at the European XFEL. In FEL2022, 2022.

Jan Kaiser, Oliver Stein and Annika Eichler. Learning-based Optimisation of Particle Accelerators Under Partial Observability Without Real-World Training. In 39th International Conference on Machine Learning (ICML), 2022.

Oliver Stein, Jan Kaiser, Annika Eichler and Ilya Agapov. Accelerating Linear Beam Dynamics Simulations for Machine Learning Applications. In 13th International Particle Accelerator Conference (IPAC), 2022.

Annika Eichler, Florian Burkart, Jan Kaiser, Willi Kuropka, Oliver Stein, Chenran Xu, Erik Bründermann and Andrea Santamaria Garcia. First Steps Toward an Autonomous Accelerator, a Common Project Between DESY and KIT. In 12th International Particle Accelerator Conference (IPAC), 2021.

Fin Hendrik Bahnsen, Jan Kaiser and Görschwin Fey. Designing Recurrent Neural Networks for Monitoring Embedded Devices. In IEEE European Test Symposium (ETS), 2021.

Jan Kaiser, Kai Bavendiek and Sibylle Schupp. Do We Need Real Data? - Testing and Training Algorithms with Artificial Geolocation Data. In INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft, 2019.

Featured talks #

Cheetah – A High-speed Differentiable Beam Dynamics Simulation for Machine Learning Applications. In 4th ICFA Beam Dynamics Mini-Workshop on Machine Learning Applications for Particle Accelerators, Gyeongju, South Korea, 2024.

Applying Reinforcement Learning to Particle Accelerators: An Introduction. In 4th ICFA Beam Dynamics Mini-Workshop on Machine Learning Applications for Particle Accelerators, Gyeongju, South Korea, 2024.

Large Language Models for Particle Accelerator Tuning. In 1st Large Language Models in Physics Symposium (LIPS), Hamburg, Germany, 2024.

Reinforcement Learning Tutorial: Application to an Accelerator Problem. In 1st Collaboration Workshop on Reinforcement Learning for Autonomous Accelerators (RL4AA'23), Karlsruhe, Germany, 2023.

Reinforcement Learning for the Optimization of Particle Accelerators. In Machine Learning in Engineering Summer School, Hamburg, Germany, 2022.

Reinforcement learning for Particle Accelerators. In MT ARD ST3 pre-meeting Machine Learning Workshop, Berlin, Germany, 2022.

Projects #

Differentiable Simulations Particle Accelerators Machine Learning PyTorch Python Package
Fast particle accelerator optics simulation built on top of PyTorch for reinforcement learning and optimisation applications, providing features like unmatched execution speeds, GPU acceleration and automatic differentiation.

RL4AA Collaboration
Community Workshops Reinforcement Learning Particle Accelerators
Co-Founding and maintenance of the Collaboration on Reinforcement Learning for Autonomous Accelerators with the goal of fostering international collaboration and knowledge exchange by organising annual workshops and providing an online platform for discussion, help and topical news.

Personal projects #

8mm Film Scanner
Film Digitisation Raspberry Pi Python Hardware Web App Post-Processing
Conversion of an old projector to a Regular 8 and Super 8 film scanner, including control software, a web app and post-processing workflow.

Shutter Speed Tester
Arduino Hardware
Simple Arduino project to test the shutter speeds of analogue cameras.