Tim Landgraf
8 papers · 2020–2024 · 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(18)
👑
Triple Crown
❓
The Questioner
Venues
Top co-authors
Research topics
Artificial Intelligence
(5)
Machine Learning
(5)
Core AI
(4)
Core Methods
(4)
Deep Learning
(2)
Computer Science
(1)
Natural Language Processing
(1)
Application Areas
(1)
Applications · Computer Science
(1)
Applications · Natural Language Processing
(1)
Learning Paradigms
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
text classification
(2)
propaganda detection
(2)
neural network
(2)
concept-based explanation
(1)
domain generalization
(1)
information bottleneck
(1)
multilingual nlp
(1)
neural network interpretability
(1)
feature attribution
(1)
neural network optimization
(1)
loss landscape
(1)
gradient estimation
(1)
weight perturbation
(1)
chaotic dynamics
(1)
temporal analysis
(1)
nearest neighbor regression
(1)
second-order optimization
(1)
support vector machine
(1)
out-of-distribution detection
(1)
interpretable model
(1)
Papers
Check News in One Click: NLP-Empowered Pro-Kremlin Propaganda Detection
EACL 2024
WeiPer: OOD Detection using Weight Perturbations of Class Projections
NeurIPS 2024
The Evolution of Pro-Kremlin Propaganda From a Machine Learning and Linguistics Perspective
EACL 2023
Chaotic Dynamics are Intrinsic to Neural Network Training with SGD
NeurIPS 2022
DNNR: Differential Nearest Neighbors Regression
ICML 2022
Do Users Benefit From Interpretable Vision? A User Study, Baseline, And Dataset
ICLR 2022
Restricting the Flow: Information Bottlenecks for Attribution
ICLR 2020
When Explanations Lie: Why Many Modified BP Attributions Fail
ICML 2020