Since 2021 Lukas is a PhD student in the Machine Learning Group at Technische Universität Berlin and a full-time researcher at the Berlin Institute for the Foundations of Learning and Data (BIFOLD). In addition, Lukas is a part-time Student Researcher at Google DeepMind and a guest researcher in the ViCCo group at the Max Planck Institute for Human Cognitive and Brain Sciences in Leipzig where he was previously employed as a Research Associate.

During his PhD Lukas was part of a research collaboration program with Google DeepMind where he was advised by Simon Kornblith. Prior to his time at the MPI, Lukas did a Master’s in IT and Cognition with a minor in Computer Science at the University of Copenhagen where he mainly worked on Natural Language Processing (NLP). His research is supported by additional funding from Google (he is essentially doing his PhD jointly at Google DeepMind and TU Berlin). Lukas’ research mainly revolves around representation learning in computer vision. He works at the intersection of Machine Learning and Cognitive Neuroscience and is mostly interested in drawing inspiration from human cognition to build general purpose machine learning algorithms.

Selected publications

• Aligning Machine and Human Visual Representations across Abstraction Levels
• Getting aligned on representational alignment
• Improving neural network representations using human similarity judgments [NeurIPS 2023]
• Human alignment of neural network representations [ICLR 2023]
• VICE: Variational Interpretable Concept Embeddings [NeurIPS 2022]