Roland S. Zimmermann
11 papers · 2020–2025 · 5 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 ↓+5 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (22) 🌍 Conference Polyglot · Silver 🐣 Hot Topic Early Bird 🏃 Academic Marathon · Sprint
🤝
Dynamic Duo
(11)
❓
The Questioner
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
🗃️
Keyword Collector
(53)
Top co-authors
Research topics
Artificial Intelligence
(6)
Machine Learning
(6)
Core AI · Artificial Intelligence
(6)
Deep Learning
(5)
Learning Types · Deep Learning
(4)
Learning Types · Machine Learning
(4)
Techniques
(3)
Application Areas
(2)
Core Methods
(2)
Optimization & Theory
(2)
Computer Vision
(1)
Architectures
(1)
Core AI · Computer Vision
(1)
Keywords
neural network
(3)
generative model
(2)
feature visualization
(2)
contrastive learning
(2)
neural network interpretability
(1)
independent component analysis
(1)
robustness
(1)
self-supervised learning
(1)
domain generalization
(1)
data augmentation
(1)
interpretability
(1)
model analysis
(1)
out-of-distribution generalization
(1)
theoretical analysis
(1)
convolutional neural network
(1)
style transfer
(1)
foundation model
(1)
ood generalization
(1)
adversarial robustness
(1)
representation learning
(1)
Papers
InfoNCE: Identifying the Gap Between Theory and Practice
AISTATS 2025
In Search of Forgotten Domain Generalization
ICLR 2025
LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models
ICML 2025
Don’t trust your eyes: on the (un)reliability of feature visualizations
ICML 2024
Measuring Per-Unit Interpretability at Scale Without Humans
NeurIPS 2024
Provably Learning Object-Centric Representations
ICML 2023
Scale Alone Does not Improve Mechanistic Interpretability in Vision Models
NeurIPS 2023
Increasing Confidence in Adversarial Robustness Evaluations
NeurIPS 2022
Contrastive Learning Inverts the Data Generating Process
ICML 2021
How Well do Feature Visualizations Support Causal Understanding of CNN Activations?
NeurIPS 2021
A Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions
ECCV 2020