Sebastian Lapuschkin
12 papers · 2016–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
๐ Academic Marathon (9) ๐งญ Keyword Pioneer ๐ Interdisciplinary Bridge ๐ Conference Polyglot (7) ๐ Cross-Pollinator (8)
๐
Renaissance Researcher
(6)
๐บ๏ธ
Taxonomy Completionist
(27)
๐
Conference Polyglot
(7)
๐
Grand Slam
๐ค
Dynamic Duo
(10)
๐
Century Club
(11)
๐๏ธ
Keyword Collector
(53)
Conferences
JMLR (3)
ACL (2)
CVPR (2)
NIPS (2)
AAAI (1)
ICLR (1)
ICML (1)
Top co-authors
Keywords
neural network
(4)
concept learning
(2)
image classification
(2)
deep neural network
(2)
generative model
(2)
explainable ai
(2)
layer-wise relevance propagation
(2)
explanation evaluation
(2)
latent representation
(2)
diffusion model
(1)
score matching
(1)
interpretability evaluation
(1)
medical imaging
(1)
adversarial learning
(1)
model adaptation
(1)
feature extraction
(1)
language model
(1)
bias mitigation
(1)
latent space
(1)
feature attribution
(1)
Papers
From Weights to Activations: Is Steering the Next Frontier of Adaptation?
ACL 2026
Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence
ICLR 2025
FADE: Why Bad Descriptions Happen to Good Features
ACL 2025
From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space
AAAI 2024
Generative Fractional Diffusion Models
NIPS 2024
AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
ICML 2024
CoSy: Evaluating Textual Explanations of Neurons
NIPS 2024
Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond
JMLR 2023
Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations
CVPR 2023
iNNvestigate Neural Networks!
JMLR 2019
The LRP Toolbox for Artificial Neural Networks
JMLR 2016
Analyzing Classifiers: Fisher Vectors and Deep Neural Networks
CVPR 2016