Thomas Serre

MTSE: Multi-Target Speaker Extraction for Conversation Scenarios Interspeech 2025 The 3D-PC: a benchmark for visual perspective taking in humans and machines ICLR 2025 Tracking objects that change in appearance with phase synchrony ICLR 2025 Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects NeurIPS 2024 Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks NeurIPS 2024 RTify: Aligning Deep Neural Networks with Human Behavioral Decisions NeurIPS 2024 Saliency strikes back: How filtering out high frequencies improves white-box explanations ICML 2024 Understanding Visual Feature Reliance through the Lens of Complexity NeurIPS 2024 A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation NeurIPS 2023 Break It Down: Evidence for Structural Compositionality in Neural Networks NeurIPS 2023 Computing a human-like reaction time metric from stable recurrent vision models NeurIPS 2023 CRAFT: Concept Recursive Activation FacTorization for Explainability CVPR 2023 Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines? ICML 2023 Don't Lie to Me! Robust and Efficient Explainability With Verified Perturbation Analysis CVPR 2023 GAMR: A Guided Attention Model for (visual) Reasoning ICLR 2023 Learning Functional Transduction NeurIPS 2023 Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex NeurIPS 2023 Unlocking Feature Visualization for Deep Network with MAgnitude Constrained Optimization NeurIPS 2023 A Benchmark for Compositional Visual Reasoning NeurIPS 2022 Diversity vs. Recognizability: Human-like generalization in one-shot generative models NeurIPS 2022 Harmonizing the object recognition strategies of deep neural networks with humans NeurIPS 2022 How and What To Learn: Taxonomizing Self-Supervised Learning for 3D Action Recognition WACV 2022 How Good Is Your Explanation? Algorithmic Stability Measures To Assess the Quality of Explanations for Deep Neural Networks WACV 2022 Meta-Reinforcement Learning with Self-Modifying Networks NeurIPS 2022 What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods NeurIPS 2022 Go with the flow: Adaptive control for Neural ODEs ICLR 2021 Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis NeurIPS 2021 Tracking Without Re-recognition in Humans and Machines NeurIPS 2021 Disentangling neural mechanisms for perceptual grouping ICLR 2020 Recurrent neural circuits for contour detection ICLR 2020 Stable and expressive recurrent vision models NeurIPS 2020 Learning what and where to attend ICLR 2019 Learning long-range spatial dependencies with horizontal gated recurrent units NeurIPS 2018 How Deep is the Feature Analysis underlying Rapid Visual Categorization? NeurIPS 2016 The Language of Actions: Recovering the Syntax and Semantics of Goal-Directed Human Activities CVPR 2014 Neural representation of action sequences: how far can a simple snippet-matching model take us? NeurIPS 2013