Hey! I'm a fourth-year PhD student in Computer Science at Stanford University, advised by Ben Van Roy. I'm broadly interested in machine learning and I am currently focused on two areas: (1) the alignment problem, and (2) developing a new framework for thinking about and evaluating continual learning.
During my Master's in Computer Science at Stanford, I worked on distributional robustness and was advised by Chelsea Finn. Before that, I worked in Andrew Ng's research group, applying deep learning to healthcare. I continued that line of work as a research fellow in Pranav Rajpurkar's group at Harvard Medical School, where I focused on creating multi-institutional datasets for medical imaging (see MAIDA). I grew up in Sweden and finished my undergraduate degree at Chalmers University of Technology.
My main interests outside of AI are playing music with friends and meditation. I'm also interested in education and during college, I co-founded Knowly, an ed-tech company focused on making corporate training more effective. More recently, I worked at Inspirit AI, a company giving live online courses for high school students in artificial intelligence and computer science.
Publications
Misalignment from Treating Means as Ends
Henrik Marklund, Alex Infanger, Benjamin Van Roy
Forthcoming in AAAI-26 Alignment Track., 2025
Continual Learning as Computationally Constrained Reinforcement Learning
Saurabh Kumar*, Henrik Marklund*, Ashish Rao, Yifan Zhu, Hong Jun Jeon, Yueyang Liu, Benjamin Van Roy
Foundations and Trends in Machine Learning, 2025
Choice Between Partial Trajectories: Disentangling Goals from Beliefs
Henrik Marklund, Benjamin Van Roy
Preprint, 2024
Maintaining Plasticity in Continual Learning via Regenerative Regularization
Saurabh Kumar*, Henrik Marklund*, Benjamin Van Roy
3rd Conference on Lifelong Learning Agents (CoLLAs), 2024
The MAIDA initiative: establishing a framework for global medical-imaging data sharing
Agustina Saenz*, Emma Chen*, Henrik Marklund, Pranav Rajpurkar
The Lancet Digital Health, 2024
Extending the WILDS benchmark for unsupervised adaptation
Shiori Sagawa*, Pang Wei Koh*, Tony Lee*, Irena Gao*, Sang Michael Xie, Kendrick Shen, Ananya Kumar, Weihua Hu, Michihiro Yasunaga, Henrik Marklund, Sara Beery, Etienne David, Ian Stavness, Wei Guo, Jure Leskovec, Kate Saenko, Tatsunori Hashimoto, Sergey Levine, Chelsea Finn, and Percy Liang
ICLR, 2022
Wilds: A benchmark of in-the-wild distribution shifts
Pang Wei Koh*, Shiori Sagawa*, Henrik Marklund, Sang Michael Xie, Marvin Zhang, Akshay Balsubramani, Weihua Hu, Michihiro Yasunaga, Richard Lanas Phillips, Irena Gao, Tony Lee, Etienne David, Ian Stavness, Wei Guo, Berton A. Earnshaw, Imran S. Haque, Sara Beery, Jure Leskovec, Anshul Kundaje, Emma Pierson, Sergey Levine, Chelsea Finn, and Percy Liang
ICML, 2021
Adaptive risk minimization: Learning to adapt to domain shift
Marvin Zhang*, Henrik Marklund*, Nikita Dhawan*, Abhishek Gupta, Sergey Levine, and Chelsea Finn
Advances in Neural Information Processing Systems, 2021
Deep learning assistance for the histopathologic diagnosis of Helicobacter pylori
Sharon Zhou*, Henrik Marklund*, Ondrej Blaha, Manisha Desai, Brock Martin, David Bingham, Gerald J. Berry, Ellen Gomulia, Andrew Y. Ng, Jeanne Shen
Intelligence-Based Medicine, 2020
Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison
Jeremy Irvin*, Pranav Rajpurkar*, Michael Ko, Yifan Yu, Silviana Ciurea-Ilcus, Chris Chute, Henrik Marklund, Behzad Haghgoo, Robyn Ball, Katie Shpanskaya, Jayne Seekins, David A. Mong, Safwan S. Halabi, Jesse K. Sandberg, Ricky Jones, David B. Larson, Curtis P. Langlotz, Bhavik N. Patel, Matthew P. Lungren, Andrew Y. Ng
Proceedings of the AAAI conference on artificial intelligence, 2019