Jens Behrmann
6 papers · 2019–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot Β· Bronze π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (12) π£ Hot Topic Early Bird
π
Triple Crown
Venues
Top co-authors
Research topics
Keywords
maximum likelihood
(2)
invertible residual network
(2)
density estimation
(2)
adversarial example
(2)
normalizing flow
(2)
distribution shift
(1)
gradient computation
(1)
generative model
(1)
adversarial perturbation
(1)
simulation-based inference
(1)
flow-based model
(1)
cross-entropy loss
(1)
bi-lipschitz constraint
(1)
change of variable
(1)
invertible neural network
(1)
adversarial vulnerability
(1)
credible interval
(1)
sensitivity-based attack
(1)
invariance-based attack
(1)
calibration set
(1)
Papers
Addressing Misspecification in Simulation-based Inference through Data-driven Calibration
ICML 2025
Understanding and Mitigating Exploding Inverses in Invertible Neural Networks
AISTATS 2021
Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations
ICML 2020
Excessive Invariance Causes Adversarial Vulnerability
ICLR 2019
Invertible Residual Networks
ICML 2019
Residual Flows for Invertible Generative Modeling
NeurIPS 2019