Holger Hermanns
3 papers · 2024–2026 · 2 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Top co-authors
Research topics
Keywords
saliency map
(2)
contrastive learning
(1)
model interpretability
(1)
deep neural network
(1)
entropy regularization
(1)
safety verification
(1)
concept bottleneck model
(1)
cross-attention mechanism
(1)
predicate abstraction
(1)
explanation quality
(1)
neural network policy
(1)
probabilistic verification
(1)
counterexample-guided abstraction refinement
(1)
image classification
(1)
semantic locality
(1)
Papers
Probabilistic Safety Verification of Neural Policies via Predicate Abstraction
AAAI 2026
SL-CBM: Enhancing Concept Bottleneck Models with Semantic Locality for Better Interpretability
AAAI 2026
Saliency Maps Give a False Sense of Explanability to Image Classifiers: An Empirical Evaluation across Methods and Metrics
ACML 2024