Julian Skirzyński

About

I am a Ph.D student in Computer Science at UCSD where I work with Berk Ustun. My research lies at the intersection of machine learning, cognitive science and human-computer interaction. I am broadly interested in integrating these areas to improve human-AI collaboration. I develop systematic frameworks to study how people interact with AI systems, identify when these interactions fail, and design interventions to help people make better decisions with AI tools.

Previously, I was a research scientist at the Max-Planck Institute where I worked with Falk Lieder on interpretable reinforcement learning and on interventions to improve human planning. I also advised Educational Entertainment One – a Polish company that developed mobile games for English language learning. I obtained M.S. in Computer Science from McGill University, M.S. in Cognitive Science from University of Warsaw, and B.S. in Mathematics and Cognitive Science from University of Warsaw. You can access my full CV here.

Selected Papers

• Preprint

  
  On the Value of Interpretability in Human Decision-Making
  Julian Skirzyński, Elena Glassman, Berk Ustun
  In Submission, 2025
  [Paper] [Code]
• FAccT

  
  Discrimination Exposed? On the Reliability of Explanations for Discrimination Detection
  Julian Skirzyński, David Danks, Berk Ustun
  ACM Conference on Fairness, Accountability, and Transparency, 2025
  [Paper] [Code]
• Computational Behavior & Behavior

  
  Automatic discovery and description of human planning strategies
  Julian Skirzyński, Yash Raj Jain, Falk Lieder
  Computational Behavior & Behavior, 2023
  [Paper] [Code]
• Computational Behavior & Behavior

  
  Boosting Human Decision‑making with AI‑Generated Decision Aids
  Federic Becker, Julian Skirzyński, Falk Lieder
  Computational Behavior & Behavior, 2022
  [Paper] [Code]
• Machine Learning Journal

  
  Automatic discovery of interpretable planning strategies
  Julian Skirzyński, Federic Becker, Falk Lieder
  Machine Learning Journal, 2021
  [Paper] [Code]
• NAACL-HLT: ViGIL Workshop

  
  Language-Conditional Imitation Learning
  Julian Skirzyński, Bobak Baghi, David Meger
  NAACL-HLT: ViGIL, 2020
  [Poster] [Paper]