Wieland Brendel

41 papers · 2011–2025 · 8 conferences · across top CS/AI conferences

Achievements

+12 more ↓

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (8) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🏃 Academic Marathon (14)

🌈 Renaissance Researcher (6) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🤝 Dynamic Duo (20) 🏆 Keyword Champion 👑 Triple Crown 🗃️ Keyword Collector (105) ❓ The Questioner (2) ⚡ Prolific Year (5) 📈 Trend Setter 💎 Century Club (41) 🔥 Unstoppable (7)

Conferences

NIPS (16) ICLR (13) ICML (7) AISTATS (1) CLEAR (1) ECCV (1) ICCV (1) JMLR (1)

Top co-authors

Matthias Bethge (20) Roland S. Zimmermann (11) Patrik Reizinger (8) Thaddäus Wiedemer (6) Evgenia Rusak (6) Robert Geirhos (6) Julius von Kügelgen (5) Yash Sharma (5) Bernhard Schölkopf (5) Attila Juhos (4)

Keywords

neural network (4) adversarial robustness (4) unsupervised learning (4) representation learning (3) self-supervised learning (3) adversarial attack (3) out-of-distribution generalization (2) gradient-based attack (2) object-centric representation (2) independent component analysis (2) generative model (2) convolutional neural network (2) defense evaluation (2) compositional generalization (2) image classification (2) adversarial example (2) object detection (1) scene understanding (1) vision transformer (1) principal component analysis (1)

Papers

VGGSounder: Audio-Visual Evaluations for Foundation Models ICCV 2025 LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models ICML 2025 Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning ICLR 2025 In Search of Forgotten Domain Generalization ICLR 2025 Cross-Entropy Is All You Need To Invert the Data Generating Process ICLR 2025 Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research ICML 2025 LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws ICML 2025 InfoNCE: Identifying the Gap Between Theory and Practice AISTATS 2025 Interaction Asymmetry: A General Principle for Learning Composable Abstractions ICLR 2025 Measuring Per-Unit Interpretability at Scale Without Humans NIPS 2024 Effective pruning of web-scale datasets based on complexity of concept clusters ICLR 2024 An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis CLEAR 2024 Does CLIP’s generalization performance mainly stem from high train-test similarity? ICLR 2024 Provable Compositional Generalization for Object-Centric Learning ICLR 2024 Position: Understanding LLMs Requires More Than Statistical Generalization ICML 2024 Don’t trust your eyes: on the (un)reliability of feature visualizations ICML 2024 Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts NIPS 2024 Compositional Generalization from First Principles NIPS 2023 Provably Learning Object-Centric Representations ICML 2023 Scale Alone Does not Improve Mechanistic Interpretability in Vision Models NIPS 2023 Visual Representation Learning Does Not Generalize Strongly Within the Same Domain ICLR 2022 Embrace the Gap: VAEs Perform Independent Mechanism Analysis NIPS 2022 Increasing Confidence in Adversarial Robustness Evaluations NIPS 2022 Benchmarking Unsupervised Object Representations for Video Sequences JMLR 2021 Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding ICLR 2021 Partial success in closing the gap between human and machine vision NIPS 2021 Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints NIPS 2021 Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style NIPS 2021 Contrastive Learning Inverts the Data Generating Process ICML 2021 How Well do Feature Visualizations Support Causal Understanding of CNN Activations? NIPS 2021 Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization ICLR 2021 On Adaptive Attacks to Adversarial Example Defenses NIPS 2020 A Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions ECCV 2020 Improving robustness against common corruptions by covariate shift adaptation NIPS 2020 ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness ICLR 2019 Accurate, reliable and fast robustness evaluation NIPS 2019 Learning from brains how to regularize machines NIPS 2019 Towards the first adversarially robust neural network model on MNIST ICLR 2019 Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet ICLR 2019 Unsupervised learning of an efficient short-term memory network NIPS 2014 Demixed Principal Component Analysis NIPS 2011