Francesco Locatello

How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations ICLR 2025 Mechanistic PDE Networks for Discovery of Governing Equations ICML 2025 Near, far: Patch-ordering enhances vision foundation models' scene understanding ICLR 2025 Scalable Mechanistic Neural Networks ICLR 2025 Score matching through the roof: linear, nonlinear, and latent variables causal discovery CLeaR 2025 Unifying Causal Representation Learning with the Invariance Principle ICLR 2025 Adaptive Slot Attention: Object Discovery with Dynamic Slot Number CVPR 2024 A Sparsity Principle for Partially Observable Causal Representation Learning ICML 2024 Grounded Object-Centric Learning ICLR 2024 Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention NeurIPS 2024 Identifying General Mechanism Shifts in Linear Causal Representations NeurIPS 2024 Latent Functional Maps: a spectral framework for representation alignment NeurIPS 2024 Marrying Causal Representation Learning with Dynamical Systems for Science NeurIPS 2024 Mechanistic Neural Networks for Scientific Machine Learning ICML 2024 Multi-View Causal Representation Learning with Partial Observability ICLR 2024 Self-Compatibility: Evaluating Causal Discovery without Ground Truth AISTATS 2024 Smoke and Mirrors in Causal Downstream Tasks NeurIPS 2024 Unsupervised Concept Discovery Mitigates Spurious Correlations ICML 2024 ASIF: Coupled Data Turns Unimodal Models to Multimodal without Training NeurIPS 2023 Assumption violations in causal discovery and the robustness of score matching NeurIPS 2023 Benign Overfitting in Deep Neural Networks under Lazy Training ICML 2023 Bridging the Gap to Real-World Object-Centric Learning ICLR 2023 Causal Discovery with Score Matching on Additive Models with Arbitrary Noise CLeaR 2023 Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning CLeaR 2023 Latent Space Translation via Semantic Alignment NeurIPS 2023 Leveraging sparse and shared feature activations for disentangled representation learning NeurIPS 2023 Object-Centric Multiple Object Tracking ICCV 2023 Relative representations enable zero-shot latent space communication ICLR 2023 Rotating Features for Object Discovery NeurIPS 2023 Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling NeurIPS 2023 Scalable Causal Discovery with Score Matching CLeaR 2023 TeST: Test-Time Self-Training Under Distribution Shift WACV 2023 Unsupervised Object Learning via Common Fate CLeaR 2023 Unsupervised Open-Vocabulary Object Localization in Videos ICCV 2023 Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations ICLR 2023 Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks NeurIPS 2022 Assaying Out-Of-Distribution Generalization in Transfer Learning NeurIPS 2022 Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization AISTATS 2022 Generalization and Robustness Implications in Object-Centric Learning ICML 2022 Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers CVPR 2022 Neural Attentive Circuits NeurIPS 2022 Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models ICML 2022 Self-supervised Amodal Video Object Segmentation NeurIPS 2022 The Role of Pretrained Representations for the OOD Generalization of RL Agents ICLR 2022 Visual Representation Learning Does Not Generalize Strongly Within the Same Domain ICLR 2022 You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction ICLR 2022 Backward-Compatible Prediction Updates: A Probabilistic Approach NeurIPS 2021 Boosting Variational Inference With Locally Adaptive Step-Sizes IJCAI 2021 Dynamic Inference with Neural Interpreters NeurIPS 2021 Neighborhood Contrastive Learning Applied to Online Patient Monitoring ICML 2021 On Disentangled Representations Learned from Correlated Data ICML 2021 On the Transfer of Disentangled Representations in Realistic Settings ICLR 2021 Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style NeurIPS 2021 A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation JMLR 2020 Disentangling Factors of Variations Using Few Labels ICLR 2020 Object-Centric Learning with Slot Attention NeurIPS 2020 Stochastic Frank-Wolfe for Constrained Finite-Sum Minimization ICML 2020 Weakly-Supervised Disentanglement Without Compromises ICML 2020 Are Disentangled Representations Helpful for Abstract Visual Reasoning? NeurIPS 2019 Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations ICML 2019 On the Fairness of Disentangled Representations NeurIPS 2019 On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset NeurIPS 2019 SOM-VAE: Interpretable Discrete Representation Learning on Time Series ICLR 2019 Stochastic Frank-Wolfe for Composite Convex Minimization NeurIPS 2019 The Incomplete Rosetta Stone problem: Identifiability results for Multi-view Nonlinear ICA UAI 2019 A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming ICML 2018 Boosting Black Box Variational Inference NeurIPS 2018 Boosting Variational Inference: an Optimization Perspective AISTATS 2018 On Matching Pursuit and Coordinate Descent ICML 2018 A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe AISTATS 2017 Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees NeurIPS 2017