Jan Sobotka

Jan Sobotka

CS Master’s Student & AI/ML Research Assistant

Swiss Federal Institute of Technology in Lausanne (EPFL)

About me

My name is Jan, I am a master’s student in computer science at EPFL and a research assistant at the MLBio Lab, where I work on unsupervised learning, multimodal foundation models, and out-of-distribution generalization. Additionally, I conduct research on world models for reinforcement learning agents at the Biorobotics Laboratory.

At a high level, I am interested in (1) understanding how our mind and cognition, as well as those of other diverse systems, work and (2) building machines that can perceive, think, and learn. This intersection of artificial intelligence and cognitive computational neuroscience excites me the most. While I approach these topics with a fairly multidisciplinary background, my primary focus is on the computational part, particularly in the following machine learning areas:

  • Representation learning
  • Data-driven control
  • (Mechanistic) interpretability
  • Meta-learning

I am always happy to discuss these topics, so if you have related thoughts or questions, please do not hesitate to contact me.


Interests
  • Representation learning
  • Data-driven control
  • (Mechanistic) interpretability
  • Meta-learning
Education
  • Master’s degree in Computer Science, 2024 - 2026

    Swiss Federal Institute of Technology in Lausanne (EPFL)

  • Bachelor’s degree in Informatics, Specialization in Artificial Intelligence, 2021 - 2024

    Czech Technical University in Prague

Recent Publications & Preprints

(2024). Enhancing Fractional Gradient Descent with Learned Optimizers. Optimization Letters (Springer).

(2024). Decoding Visual Stimuli from Cortical Activity using Neural Networks. Bachelor’s Thesis, Czech Technical University Digital Library.

PDF

(2024). Investigation into the Training Dynamics of Learned Optimizers. 16th International Conference on Agents and Artificial Intelligence (ICAART 2024).

PDF DOI

(2024). Investigation into Training Dynamics of Learned Optimizers (Student Abstract). The 38th Annual AAAI Conference on Artificial Intelligence (AAAI-24).

PDF DOI