Klas Wijk

PhD Student at KTH Royal Institute of Technology

photo.png

Lindstedtsvägen 24

Stockholm, Sweden

About

I am a PhD student in Computer Science (Machine Learning) at the Division of Robotics, Perception and Learning (RPL), supervised by Hossein Azizpour, and co-supervised by Ricardo Vinuesa Motilva at the Department of Engineering Mechanics and Vinuesa Lab.

My research interests include deep generative models, inverse problems, feature selection, and physics-constrained learning for fluid mechanics. I received a BSc in Computer Science and an MSc in Applied and Computational Mathematics at KTH.

I am fully funded by the Swedish e-Science Research Centre (SeRC) and part of their Multidisciplinary Collaboration Program (MCP) in Data Science, led by Hedvig Kjellström. Additionally, I am part of the Wallenberg AI, Autonomous Systems and Software Program (WASP), the largest research program in Sweden. As a WASP student, I am enrolled in their graduate school.

News

Oct 31, 2025 Poster accepted to the EurIPS’25 DiffSys Workshop in Copenhagen! 🇩🇰
Oct 14, 2025 Poster accepted to the ELLIS UnConference in Copenhagen! 🇩🇰
Apr 28, 2025 Attended ICLR 2025 in Singapore and presented a poster! 🇸🇬
Jan 22, 2025 Paper accepted to ICLR 2025.
Oct 30, 2024 Participated in the Poland Open Hackathon. 🇵🇱

Selected publications

  1. Differentiable Top-k: From One-Hot to k-Hot
    Klas Wijk, Ricardo Vinuesa, and Hossein Azizpour
    EurIPS 2025 Workshop on Differentiable Systems and Scientific Machine Learning, 2025
  2. SFESS: Score Function Estimators for k-Subset Sampling
    Klas Wijk, Ricardo Vinuesa, and Hossein Azizpour
    International Conference on Learning Representations, 2025
  3. Revisiting Score Function Estimators for k-Subset Sampling
    Klas Wijk, Ricardo Vinuesa, and Hossein Azizpour
    ICML 2024 Workshop on Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators, 2024
  4. Indirectly Parameterized Concrete Autoencoders
    Alfred Nilsson, Klas Wijk, Sai Gutha, and 7 more authors
    International Conference on Machine Learning, 2024

Academic Service

Reviewer for ICLR 2026
Reviewer for EurIPS 2025 Workshop on Differentiable Systems and Scientific Machine Learning
Reviewer for ICLR 2025
Reviewer for ICML 2024 Workshop on Differentiable Almost Everything