Mateusz Jurewicz
Scholar

Mateusz Jurewicz

Google Scholar ID: VYr8R8wAAAAJ
Ph.D., IT University of Copenhagen
machine learningartificial intelligencestructure predictionmechanistic interpretabilityai
Citations & Impact
All-time
Citations
31
 
H-index
3
 
i10-index
1
 
Publications
7
 
Co-authors
3
list available
Resume (English only)
Academic Achievements
  • DarkBench: Benchmarking Dark Patterns in Large Language Models, ICLR 2025
  • Artificial Intelligence and Privacy: Causes for Concern, PSJ 2024
  • The Catalog Problem: Clustering and Ordering Variable-Sized Sets, ICML 2023
  • Set Interdependence Transformer: Set-to-Sequence Neural Networks for Permutation Learning and Structure Prediction, IJCAI-ECAI 2022
  • PROCAT: Product Catalogue Dataset for Implicit Clustering, Permutation Learning and Structure Prediction, NeurIPS 2021
  • Set-to-Sequence Methods in Machine Learning, JAIR 2021
Research Experience
  • Worked at scale-ups like Tjek A/S and large tech companies like Intel.
Education
  • Ph.D. in Computer Science from IT University of Copenhagen, advised by Professor Leon Derczynski. Also advised by Professor Graham Taylor during a research stay at the Vector Institute for Artificial Intelligence and the University of Guelph’s Machine Learning Research Group in Canada.
Background
  • Senior Machine Learning Engineer and AI Researcher interested in safely deploying AI models to help understand and solve real-world challenges. Research interests include generative models (NLP, LLMs) and reinforcement learning, with a focus on building multimodal, scalable, and interpretable intelligent systems. Other research interests include technical AI safety, mechanistic interpretability, and scalable oversight.
Miscellany
  • Contact: Email: mateusz.jurewicz@gmail.com, Phone: (+45) 20 88 35 32