Michał Wiliński

About

I am an incoming PhD student at the Robotics Institute at Carnegie Mellon University, starting in Fall 2026. I am interested in building machine learning systems that are more capable, steerable, and useful in practice, with current work centered on imitation learning and reinforcement learning, with applications in modern ML systems, especially language models.

I completed my B.Sc. in Artificial Intelligence at Poznan University of Technology. My undergrad thesis, DetoxAI, explored debiasing deep learning models in computer vision. Previously, I worked on pretrained time series models and interpretability with the Auton Lab. Earlier projects also covered SLAM for space and industrial environments, neurosymbolic NLP, and LLM assistants.

Research Interests

I am broadly interested in machine learning systems that learn efficiently from human feedback, demonstrations, and interaction. Lately I have been especially interested in how demonstration, feedback, and interaction can be used to train more capable and reliable language-model-based systems.

Education

• Carnegie Mellon University — PhD, Robotics Institute, School of Computer Science. Deferred admit, starting Fall 2026.
• Poznan University of Technology — B.Sc. in Artificial Intelligence, 2021–2025.

Selected Publications

For a complete list, see my Google Scholar profile.

• Exploring Representations and Interventions in Time Series Foundation Models
  M. Wiliński, M. Goswami, W. Potosnak, N. Żukowska, and A. Dubrawski. ICML 2025, Vancouver.
• TimeSeriesGym: A Scalable Benchmark for Time Series ML Engineering Agents
  Y. Cai, X. Li, M. Goswami, M. Wiliński, G. Welter, and A. Dubrawski. arXiv:2505.13291.
• DetoxAI: A Python Toolkit for Debiasing Deep Learning Models in Computer Vision
  I. Stępka, Ł. Sztukiewicz, M. Wiliński, and J. Stefanowski. ECML-PKDD 2025, Porto.