Robert Geirhos
18 papers · 2018–2026 · 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 ↓+10 more ↓ Show less ↑
🗺️ Taxonomy Completionist (34) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird
🏆
Keyword Champion
(3)
🧭
Keyword Pioneer
🧬
Topic Evolution
👥
Mega-Team · Squad
❓
The Questioner
(3)
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
⚡
Prolific Year · Productive
🗃️
Keyword Collector
(86)
📈
Trend Setter
Venues
Top co-authors
Research topics
Machine Learning
(13)
Deep Learning
(9)
Artificial Intelligence
(8)
Core AI
(8)
Computer Vision
(6)
Learning Types · Machine Learning
(6)
Application Areas
(5)
Optimization & Theory
(5)
Analysis
(4)
Architectures
(4)
Core Methods
(4)
Learning Types · Deep Learning
(4)
Interdisciplinary
(2)
Cognitive Science
(1)
Generation
(1)
Keywords
convolutional neural network
(5)
vision transformer
(3)
feature visualization
(3)
interpretability
(2)
image classification
(2)
object recognition
(2)
neural network
(2)
shape bia
(2)
activation maximization
(2)
model comparison
(2)
robustness
(1)
video generation
(1)
self-supervised learning
(1)
data augmentation
(1)
contrastive learning
(1)
object detection
(1)
visual object recognition
(1)
embedding
(1)
benchmark evaluation
(1)
abstraction
(1)
Papers
Do Generative Video Models Understand Physical Principles?
WACV 2026
Can We Talk Models Into Seeing the World Differently?
ICLR 2025
LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models
ICML 2025
Learning Visual Composition through Improved Semantic Guidance
CVPR 2025
Position: We Can’t Understand AI Using our Existing Vocabulary
ICML 2025
Towards flexible perception with visual memory
ICML 2025
Don’t trust your eyes: on the (un)reliability of feature visualizations
ICML 2024
Intriguing Properties of Generative Classifiers
ICLR 2024
Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
NeurIPS 2023
Scaling Vision Transformers to 22 Billion Parameters
ICML 2023
Beyond neural scaling laws: beating power law scaling via data pruning
NeurIPS 2022
Trivial or Impossible --- dichotomous data difficulty masks model differences (on ImageNet and beyond)
ICLR 2022
Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization
ICLR 2021
How Well do Feature Visualizations Support Causal Understanding of CNN Activations?
NeurIPS 2021
Partial success in closing the gap between human and machine vision
NeurIPS 2021
Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency
NeurIPS 2020
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
ICLR 2019
Generalisation in humans and deep neural networks
NeurIPS 2018