Jörn-Henrik Jacobsen

Computer Science · Physical Sciences

17h-index2.7kcitations36works1.02yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Generative Adversarial Networks and Image Synthesis(10), Adversarial Robustness in Machine Learning(10), Model Reduction and Neural Networks(7), Neural Networks and Applications(6), Domain Adaptation and Few-Shot Learning(5)

Publications36 total

Inferring Optical Tissue Properties from Photoplethysmography using Hybrid Amortized Inference
arXiv (Cornell University)·2025· 1 citedOpen Access
Leveraging Cardiovascular Simulations for In-Vivo Prediction of Cardiac Biomarkers
arXiv (Cornell University)·2024Open Access
Considerations for Distribution Shift Robustness of Diagnostic Models in Healthcare
arXiv (Cornell University)·2024Open Access
Addressing Misspecification in Simulation-based Inference through Data-driven Calibration
arXiv (Cornell University)·2024· 3 citedOpen Access
Simulation-based Inference for Cardiovascular Models
arXiv (Cornell University)·2023· 2 citedOpen Access
Learning Invariant Representations with Missing Data.
PubMed·2022· 2 citedOpen Access
Robust Hybrid Learning With Expert Augmentation
arXiv (Cornell University)·2022· 5 citedOpen Access
Learning Invariant Representations with Missing Data
arXiv (Cornell University)·2021Open Access
Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling
International Conference on Machine Learning·2020· 20 cited
How to Train Your Neural ODE: the World of Jacobian and Kinetic Regularization
International Conference on Machine Learning·2020· 29 cited
Shortcut learning in deep neural networks
Nature Machine Intelligence·2020· 1.6k citedOpen Access
Unintended cue learning: Lessons for deep learning from experimental psychology
Journal of Vision·2020· 1 citedOpen Access
Environment Inference for Invariant Learning
arXiv (Cornell University)·2020· 10 citedOpen Access
How to train your Neural ODE
2020· 27 cited
Understanding and Mitigating Exploding Inverses in Invertible Neural Networks
arXiv (Cornell University)·2020· 18 citedOpen Access
Understanding and Mitigating Exploding Inverses in Invertible Neural\n Networks
arXiv (Cornell University)·2020· 17 citedOpen Access
Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling
arXiv (Cornell University)·2020· 15 citedOpen Access
Cutting out the Middle-Man: Training and Evaluating Energy-Based Models without Sampling
arXiv (Cornell University)·2020· 9 citedOpen Access
Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations
arXiv (Cornell University)·2020· 29 citedOpen Access
How to train your neural ODE: the world of Jacobian and kinetic regularization
arXiv (Cornell University)·2020· 76 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Jens Behrmann(13), Richard S. Zemel(9), Kuan-Chieh Wang(7), David Duvenaud(6), Will Grathwohl(5), A.W.M. Smeulders(5), Antoine Wehenkel(5), Guillermo Sapiro(5), Roger Grosse(4), Matthias Bethge(3), Chris Finlay(3), Levon Nurbekyan(3), Adam M. Oberman(3), Florian Tramèr(3), Nicholas Carlini(3), Nicolas Papernot(3), Paul Vicol(3), Ozan Şener(3), Marco Cuturi(3), Andrew C. Miller(3)