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.