Thomas Fel - RankMe

70 papers A* 20A 1Journal 45Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Bi-Orthogonal Factor Decomposition for Vision Transformers. CoRR Fenil R. Doshi, Thomas Fel, Talia Konkle, George A. Alvarez
2026	J	`jnl`	Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings. CoRR Grégoire Dhimoïla, Thomas Fel, Victor Boutin, Agustin M. Picard
2026	J	`jnl`	Interpreting Physics in Video World Models. CoRR Sonia Joseph, Quentin Garrido, Randall Balestriero, Matthew Kowal, Thomas Fel, Shahab Bakhtiari, Blake A. Richards, Mike Rabbat
2025	J	`jnl`	A Geometric Unification of Concept Learning with Concept Cones. CoRR Alexandre Rocchi-Henry, Thomas Fel, Gianni Franchi
2025	A*	`conf`	An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures. ICML Thibaut Boissin, Franck Mamalet, Thomas Fel, Agustin Martin Picard, Thomas Massena, Mathieu Serrurier
2025	J	`jnl`	An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures. CoRR Thibaut Boissin, Franck Mamalet, Thomas Fel, Agustin Martin Picard, Thomas Massena, Mathieu Serrurier
2025	A*	`conf`	Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models. ICML Thomas Fel, Ekdeep Singh Lubana, Jacob S. Prince, Matthew Kowal, Victor Boutin, Isabel Papadimitriou, Binxu Wang, Martin Wattenberg, Demba E. Ba, Talia Konkle
2025	J	`jnl`	Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models. CoRR Thomas Fel, Ekdeep Singh Lubana, Jacob S. Prince, Matthew Kowal, Victor Boutin, Isabel Papadimitriou, Binxu Wang, Martin Wattenberg, Demba E. Ba, Talia Konkle
2025	J	`jnl`	Back to the Baseline: Examining Baseline Effects on Explainability Metrics. CoRR Agustin Martin Picard, Thibaut Boissin, Varshini Subhash, Rémi Cadène, Thomas Fel
2025	J	`jnl`	Block-Recurrent Dynamics in Vision Transformers. CoRR Mozes Jacobs, Thomas Fel, Richard Hakim, Alessandra Brondetta, Demba E. Ba, T. Andy Keller
2025	J	`jnl`	Evaluating Sparse Autoencoders: From Shallow Design to Matching Pursuit. CoRR Valérie Costa, Thomas Fel, Ekdeep Singh Lubana, Bahareh Tolooshams, Demba E. Ba
2025	J	`jnl`	From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit. CoRR Valérie Costa, Thomas Fel, Ekdeep Singh Lubana, Bahareh Tolooshams, Demba E. Ba
2025	J	`jnl`	Interpreting the Linear Structure of Vision-language Model Embedding Spaces. CoRR Isabel Papadimitriou, Huangyuan Su, Thomas Fel, Naomi Saphra, Sham M. Kakade, Stephanie Gil
2025	J	`jnl`	Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry. CoRR Thomas Fel, Binxu Wang, Michael A. Lepori, Matthew Kowal, Andrew Lee, Randall Balestriero, Sonia Joseph, Ekdeep Singh Lubana, Talia Konkle, Demba E. Ba, Martin Wattenberg
2025	A*	`conf`	One Wave To Explain Them All: A Unifying Perspective On Feature Attribution. ICML Gabriel Kasmi, Amandine Brunetto, Thomas Fel, Jayneel Parekh
2025	J	`jnl`	Priors in Time: Missing Inductive Biases for Language Model Interpretability. CoRR Ekdeep Singh Lubana, Can Rager, Sai Sumedh R. Hindupur, Valérie Costa, Greta Tuckute, Oam Patel, Sonia Krishna Murthy, Thomas Fel, Daniel Wurgaft, Eric J. Bigelow, Johnny Lin, Demba E. Ba, Martin Wattenberg, Fernanda B. Viégas, Melanie Weber, Aaron Mueller
2025	J	`jnl`	Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry. CoRR Sai Sumedh R. Hindupur, Ekdeep Singh Lubana, Thomas Fel, Demba E. Ba
2025	J	`jnl`	Sparks of Explainability: Recent Advancements in Explaining Large Vision Models. CoRR Thomas Fel
2025	J	`jnl`	Sparse, self-organizing ensembles of local kernels detect rare statistical anomalies. CoRR Gaia Grosso, Sai Sumedh R. Hindupur, Thomas Fel, Samuel Bright-Thonney, Philip C. Harris, Demba E. Ba
2025	J	`jnl`	Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders. CoRR Matyas Bohacek, Thomas Fel, Maneesh Agrawala, Ekdeep Singh Lubana
2025	A*	`conf`	Unearthing Skill-level Insights for Understanding Trade-offs of Foundation Models. ICLR Mazda Moayeri, Vidhisha Balachandran, Varun Chandrasekaran, Safoora Yousefi, Thomas Fel, Soheil Feizi, Besmira Nushi, Neel Joshi, Vibhav Vineet
2025	A*	`conf`	Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment. ICML Harrish Thasarathan, Julian Forsyth, Thomas Fel, Matthew Kowal, Konstantinos G. Derpanis
2025	J	`jnl`	Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment. CoRR Harrish Thasarathan, Julian Forsyth, Thomas Fel, Matthew Kowal, Konstantinos G. Derpanis
2025	J	`jnl`	Visual Anagrams Reveal Hidden Differences in Holistic Shape Processing Across Vision Models. CoRR Fenil R. Doshi, Thomas Fel, Talia Konkle, George A. Alvarez
2024	J	`jnl`	Conformal prediction for trustworthy detection of railway signals. AI Ethics Léo Andéol, Thomas Fel, Florence de Grancey, Luca Mossina
2024	J	`jnl`	Feature Accentuation: Revealing 'What' Features Respond to in Natural Images. CoRR Chris J. Hamblin, Thomas Fel, Srijani Saha, Talia Konkle, George A. Alvarez
2024	—	`conf`	Influenciæ: A Library for Tracing the Influence Back to the Data-Points. xAI (4) Agustin M. Picard, Lucas Hervier, Thomas Fel, David Vigouroux
2024	A*	`conf`	Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks. NeurIPS Victor Boutin, Rishav Mukherji, Aditya Agrawal, Sabine Muzellec, Thomas Fel, Thomas Serre, Rufin VanRullen
2024	J	`jnl`	Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks. CoRR Victor Boutin, Rishav Mukherji, Aditya Agrawal, Sabine Muzellec, Thomas Fel, Thomas Serre, Rufin VanRullen
2024	J	`jnl`	Local vs distributed representations: What is the right basis for interpretability? CoRR Julien Colin, Lore Goetschalckx, Thomas Fel, Victor Boutin, Jay Gopal, Thomas Serre, Nuria Oliver
2024	A*	`conf`	On the Foundations of Shortcut Learning. ICLR Katherine L. Hermann, Hossein Mobahi, Thomas Fel, Michael Curtis Mozer
2024	J	`jnl`	One Wave to Explain Them All: A Unifying Perspective on Post-hoc Explainability. CoRR Gabriel Kasmi, Amandine Brunetto, Thomas Fel, Jayneel Parekh
2024	A*	`conf`	Saliency strikes back: How filtering out high frequencies improves white-box explanations. ICML Sabine Muzellec, Thomas Fel, Victor Boutin, Léo Andéol, Rufin VanRullen, Thomas Serre
2024	—	`—`	Sparks of Explainability: Recent Advancements in Explaining Large Vision Models. (Lueurs d'Explicabilité : Avancées Récentes dans l'Explication des Grands Modèles de Vision). Thomas Fel
2024	A*	`conf`	Understanding Visual Feature Reliance through the Lens of Complexity. NeurIPS Thomas Fel, Louis Béthune, Andrew K. Lampinen, Thomas Serre, Katherine L. Hermann
2024	J	`jnl`	Understanding Visual Feature Reliance through the Lens of Complexity. CoRR Thomas Fel, Louis Béthune, Andrew Kyle Lampinen, Thomas Serre, Katherine L. Hermann
2024	J	`jnl`	Unearthing Skill-Level Insights for Understanding Trade-Offs of Foundation Models. CoRR Mazda Moayeri, Vidhisha Balachandran, Varun Chandrasekaran, Safoora Yousefi, Thomas Fel, Soheil Feizi, Besmira Nushi, Neel Joshi, Vibhav Vineet
2023	A*	`conf`	A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation. NeurIPS Thomas Fel, Victor Boutin, Louis Béthune, Rémi Cadène, Mazda Moayeri, Léo Andéol, Mathieu Chalvidal, Thomas Serre
2023	J	`jnl`	A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation. CoRR Thomas Fel, Victor Boutin, Mazda Moayeri, Rémi Cadène, Louis Béthune, Léo Andéol, Mathieu Chalvidal, Thomas Serre
2023	J	`jnl`	Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception. CoRR Drew Linsley, Pinyuan Feng, Thibaut Boissin, Alekh Karkada Ashok, Thomas Fel, Stephanie Olaiya, Thomas Serre
2023	J	`jnl`	COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks. CoRR Fanny Jourdan, Agustin Martin Picard, Thomas Fel, Laurent Risser, Jean-Michel Loubes, Nicholas Asher
2023	—	`conf`	COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP. ACL (Findings) Fanny Jourdan, Agustin Martin Picard, Thomas Fel, Laurent Risser, Jean-Michel Loubes, Nicholas Asher
2023	A*	`conf`	CRAFT: Concept Recursive Activation FacTorization for Explainability. CVPR Thomas Fel, Agustin Martin Picard, Louis Béthune, Thibaut Boissin, David Vigouroux, Julien Colin, Rémi Cadène, Thomas Serre
2023	—	`conf`	Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signaling. COPA Léo Andéol, Thomas Fel, Florence de Grancey, Luca Mossina
2023	J	`jnl`	Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signaling. CoRR Léo Andéol, Thomas Fel, Florence de Grancey, Luca Mossina
2023	A*	`conf`	Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines? ICML Victor Boutin, Thomas Fel, Lakshya Singhal, Rishav Mukherji, Akash Nagaraj, Julien Colin, Thomas Serre
2023	J	`jnl`	Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines? CoRR Victor Boutin, Thomas Fel, Lakshya Singhal, Rishav Mukherji, Akash Nagaraj, Julien Colin, Thomas Serre
2023	A*	`conf`	Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis. CVPR Thomas Fel, Melanie Ducoffe, David Vigouroux, Rémi Cadène, Mikael Capelle, Claire Nicodème, Thomas Serre
2023	J	`jnl`	Gradient strikes back: How filtering out high frequencies improves explanations. CoRR Sabine Muzellec, Léo Andéol, Thomas Fel, Rufin VanRullen, Thomas Serre
2023	J	`jnl`	On the Foundations of Shortcut Learning. CoRR Katherine L. Hermann, Hossein Mobahi, Thomas Fel, Michael C. Mozer
2023	A*	`conf`	On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective. NeurIPS Mathieu Serrurier, Franck Mamalet, Thomas Fel, Louis Béthune, Thibaut Boissin
2023	A*	`conf`	Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex. NeurIPS Drew Linsley, Ivan F. Rodriguez Rodriguez, Thomas Fel, Michael Arcaro, Saloni Sharma, Margaret S. Livingstone, Thomas Serre
2023	J	`jnl`	Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex. CoRR Drew Linsley, Ivan Felipe Rodríguez, Thomas Fel, Michael Arcaro, Saloni Sharma, Margaret S. Livingstone, Thomas Serre
2023	A*	`conf`	Unlocking Feature Visualization for Deep Network with MAgnitude Constrained Optimization. NeurIPS Thomas Fel, Thibaut Boissin, Victor Boutin, Agustin M. Picard, Paul Novello, Julien Colin, Drew Linsley, Tom Rousseau, Rémi Cadène, Lore Goetschalckx, Laurent Gardes, Thomas Serre
2023	J	`jnl`	Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization. CoRR Thomas Fel, Thibaut Boissin, Victor Boutin, Agustin Martin Picard, Paul Novello, Julien Colin, Drew Linsley, Tom Rousseau, Rémi Cadène, Laurent Gardes, Thomas Serre
2022	J	`jnl`	CRAFT: Concept Recursive Activation FacTorization for Explainability. CoRR Thomas Fel, Agustin Martin Picard, Louis Béthune, Thibaut Boissin, David Vigouroux, Julien Colin, Rémi Cadène, Thomas Serre
2022	J	`jnl`	Conviformers: Convolutionally guided Vision Transformer. CoRR Mohit Vaishnav, Thomas Fel, Ivan Felipe Rodríguez, Thomas Serre
2022	J	`jnl`	Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis. CoRR Thomas Fel, Melanie Ducoffe, David Vigouroux, Rémi Cadène, Mikael Capelle, Claire Nicodeme, Thomas Serre
2022	A*	`conf`	Harmonizing the object recognition strategies of deep neural networks with humans. NeurIPS Thomas Fel, Ivan F. Rodriguez Rodriguez, Drew Linsley, Thomas Serre
2022	J	`jnl`	Harmonizing the object recognition strategies of deep neural networks with humans. CoRR Thomas Fel, Ivan Felipe Rodríguez, Drew Linsley, Thomas Serre
2022	A	`conf`	How Good is your Explanation? Algorithmic Stability Measures to Assess the Quality of Explanations for Deep Neural Networks. WACV Thomas Fel, David Vigouroux, Rémi Cadène, Thomas Serre
2022	A*	`conf`	Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure. NeurIPS Paul Novello, Thomas Fel, David Vigouroux
2022	J	`jnl`	Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure. CoRR Paul Novello, Thomas Fel, David Vigouroux
2022	A*	`conf`	What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods. NeurIPS Julien Colin, Thomas Fel, Rémi Cadène, Thomas Serre
2022	J	`jnl`	When adversarial attacks become interpretable counterfactual explanations. CoRR Mathieu Serrurier, Franck Mamalet, Thomas Fel, Louis Béthune, Thibaut Boissin
2022	J	`jnl`	Xplique: A Deep Learning Explainability Toolbox. CoRR Thomas Fel, Lucas Hervier, David Vigouroux, Antonin Poché, Justin Plakoo, Rémi Cadène, Mathieu Chalvidal, Julien Colin, Thibaut Boissin, Louis Béthune, Agustin Martin Picard, Claire Nicodeme, Laurent Gardes, Grégory Flandin, Thomas Serre
2021	A*	`conf`	Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis. NeurIPS Thomas Fel, Rémi Cadène, Mathieu Chalvidal, Matthieu Cord, David Vigouroux, Thomas Serre
2021	J	`jnl`	Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis. CoRR Thomas Fel, Rémi Cadène, Mathieu Chalvidal, Matthieu Cord, David Vigouroux, Thomas Serre
2021	J	`jnl`	What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods. CoRR Thomas Fel, Julien Colin, Rémi Cadène, Thomas Serre
2020	J	`jnl`	Representativity and Consistency Measures for Deep Neural Network Explanations. CoRR Thomas Fel, David Vigouroux