← Authors

Thomas FEL

22 papers · 2021–2025 · 6 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (6) 🐝 Cross-Pollinator (9) 🌈 Renaissance Researcher (6) πŸ—ΊοΈ Taxonomy Completionist (26) πŸ‘‘ Triple Crown 🀝 Dynamic Duo (13) ❓ The Questioner (2) ⚑ Prolific Year (8) πŸ—ƒοΈ Keyword Collector (65) πŸ“ˆ Trend Setter πŸ’Ž Century Club (22) πŸ”₯ Unstoppable (5)

Conferences

NIPS (10) ICML (6) CVPR (2) ICLR (2) ACL (1) WACV (1)

Top co-authors

Thomas Serre (13) Remi Cadene (7) Victor Boutin (6) David Vigouroux (5) Louis BΓ©thune (4) Julien Colin (4) Thibaut Boissin (4) Agustin PICARD (3) Drew Linsley (3) Paul Novello (2)

Keywords

deep neural network (3) visual feature (3) explainable ai (3) attribution method (3) representation learning (3) image generation (2) image classification (2) concept-based explanation (2) object recognition (2) explainability method (2) neural network (2) concept importance (2) concept extraction (2) neural network interpretability (2) sensitivity analysis (2) neural harmonizer (2) interpretable machine learning (1) optimal transport (1) prototype learning (1) adversarial robustness (1)

Papers

Unearthing Skill-level Insights for Understanding Trade-offs of Foundation Models ICLR 2025
Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models ICML 2025
One Wave To Explain Them All: A Unifying Perspective On Feature Attribution ICML 2025
Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment ICML 2025
An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures ICML 2025
Saliency strikes back: How filtering out high frequencies improves white-box explanations ICML 2024
Understanding Visual Feature Reliance through the Lens of Complexity NIPS 2024
Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks NIPS 2024
On the Foundations of Shortcut Learning ICLR 2024
Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines? ICML 2023
COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP ACL 2023
CRAFT: Concept Recursive Activation FacTorization for Explainability CVPR 2023
Don't Lie to Me! Robust and Efficient Explainability With Verified Perturbation Analysis CVPR 2023
Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex NIPS 2023
On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective NIPS 2023
A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation NIPS 2023
Unlocking Feature Visualization for Deep Network with MAgnitude Constrained Optimization NIPS 2023
How Good Is Your Explanation? Algorithmic Stability Measures To Assess the Quality of Explanations for Deep Neural Networks WACV 2022
What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods NIPS 2022
Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure NIPS 2022
Harmonizing the object recognition strategies of deep neural networks with humans NIPS 2022
Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis NIPS 2021