Gerhard Wunder
4 papers · 2024–2026 · 3 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
Top co-authors
Keywords
feature attribution
(2)
black-box setting
(2)
latent feature discovery
(1)
deep learning model
(1)
sparse projection
(1)
mechanistic interpretability
(1)
hallucination detection
(1)
integrated gradient
(1)
model decision
(1)
shapley value
(1)
latent feature
(1)
attribution method
(1)
explanation evaluation
(1)
image data
(1)
model steering
(1)
latent direction
(1)
path method
(1)
input manipulation
(1)
gradient-like explanation
(1)
white-box
(1)
Papers
Rethinking Explanation Evaluation Under the Retraining Scheme
AAAI 2026
GEFA: A General Feature Attribution Framework Using Proxy Gradient Estimation
ICML 2025
Where Confabulation Lives: Latent Feature Discovery in LLMs
EMNLP 2025
On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-box
ICML 2024