Sotabase

Career

· Undergraduate Degree, Chalmers University of Technology
· Researcher, Harvard Medical School
· Instructor, Inspirit AI
· Co-founder, Knowly
· Master's in Computer Science, Stanford University
· PhD in Computer Science, Stanford University
· Research in Andrew Ng's research group, Stanford University

Publications (17)

CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison
AAAI Conference on Artificial Intelligence · 2019
3,120
cited
WILDS: A Benchmark of in-the-Wild Distribution Shifts
International Conference on Machine Learning · 2020
1,671
cited
Adaptive Risk Minimization: Learning to Adapt to Domain Shift
Neural Information Processing Systems · 2020
246
cited
Extending the WILDS Benchmark for Unsupervised Adaptation
International Conference on Learning Representations · 2021
113
cited
Adaptive Risk Minimization: A Meta-Learning Approach for Tackling Group Shift
arXiv.org · 2020
86
cited
Continual Learning as Computationally Constrained Reinforcement Learning
Found. Trends Mach. Learn. · 2023
37
cited
Maintaining Plasticity in Continual Learning via Regenerative Regularization
CoLLAs · 2023
36
cited
Deep learning assistance for the histopathologic diagnosis of Helicobacter pylori
2020
28
cited
Out-of-Distribution Detection Methods Answer the Wrong Questions
arXiv.org · 2025
9
cited
Test-Time Alignment via Hypothesis Reweighting
arXiv.org · 2024
7
cited
Exact (Then Approximate) Dynamic Programming for Deep Reinforcement Learning
2020
3
cited
Deep learning-based Helicobacter pylori detection: A diagnostic pathology study
medRxiv · 2020
1
cited
2022 Source Labeled Unlabeled Belgium France Norway Validation China Target United States Canada UK Japan Mexico Extra
2022
International Retrospective Observational Study of Continual Learning for AI on Endotracheal Tube Placement from Chest Radiographs
NEJM AI · 2025
The impact of a negative repo rate on corporate financing decisions: the Swedish case
2017
Turning Equations into Latex : Pipeline vs . End-to-End
Sotabase
Henrik Marklund | Researcher Profile | Sotabase | Sotabase