Bernhard Schölkopf

PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers in Overleaf ACL 2026 How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities EACL 2026 When Do Language Models Endorse Limitations on Human Rights Principles? EACL 2026 On the Emergence and Test-Time Use of Structural Information in Large Language Models ACL 2026 Test of Time: Rethinking Temporal Signal of Benchmark Contamination ACL 2026 The Directionality of Optimization Trajectories in Neural Networks ICLR 2025 Generative Intervention Models for Causal Perturbation Modeling ICML 2025 Learning Joint Interventional Effects from Single-Variable Interventions in Additive Models ICML 2025 Orthogonal Finetuning Made Scalable EMNLP 2025 Standardizing Structural Causal Models ICLR 2025 MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs ICLR 2025 Accuracy on the wrong line: On the pitfalls of noisy data for out-of-distribution generalisation AISTATS 2025 Voices of Her: Analyzing Gender Differences in the AI Publication World ACL 2025 Improving Large Language Model Safety with Contrastive Representation Learning EMNLP 2025 Are Language Models Consequentialist or Deontological Moral Reasoners? EMNLP 2025 Quriosity: Analyzing Human Questioning Behavior and Causal Inquiry through Curiosity-Driven Queries AACL 2025 DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal ACL 2025 Language Model Alignment in Multilingual Trolley Problems ICLR 2025 Algorithmic causal structure emerging through compression CLEAR 2025 Can Large Language Models Understand Symbolic Graphics Programs? ICLR 2025 Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy Filtering ICLR 2025 Quriosity: Analyzing Human Questioning Behavior and Causal Inquiry through Curiosity-Driven Queries IJCNLP 2025 Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning ICLR 2025 Preference Elicitation for Offline Reinforcement Learning ICLR 2025 Generalized Interpolating Discrete Diffusion ICML 2025 Detecting and Identifying Selection Structure in Sequential Data ICML 2024 Safe & Accurate at Speed with Tendons: A Robot Arm for Exploring Dynamic Motion RSS 2024 Causal Modeling with Stationary Diffusions AISTATS 2024 Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization ICLR 2024 Skill or Luck? Return Decomposition via Advantage Functions ICLR 2024 Ghost on the Shell: An Expressive Representation of General 3D Shapes ICLR 2024 Out-of-Variable Generalisation for Discriminative Models ICLR 2024 Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding ICLR 2024 GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs CVPR 2024 The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks. ICLR 2024 A diverse Multilingual News Headlines Dataset from around the World NAACL 2024 The Odyssey of Commonsense Causality: From Foundational Benchmarks to Cutting-Edge Reasoning EMNLP 2024 Do LLMs Think Fast and Slow? A Causal Study on Sentiment Analysis EMNLP 2024 Implicit Personalization in Language Models: A Systematic Study EMNLP 2024 Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis EMNLP 2024 Identifying Policy Gradient Subspaces ICLR 2024 Can Large Language Models Infer Causation from Correlation? ICLR 2024 Targeted Reduction of Causal Models UAI 2024 Products, Abstractions and Inclusions of Causal Spaces UAI 2024 Analyzing the Role of Semantic Representations in the Era of Large Language Models NAACL 2024 Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners? ICML 2024 Geometry-Aware Instrumental Variable Regression ICML 2024 Provable Privacy with Non-Private Pre-Processing ICML 2024 Robustness of Nonlinear Representation Learning ICML 2024 Causal vs. Anticausal merging of predictors NIPS 2024 Limits of Transformer Language Models on Learning to Compose Algorithms NIPS 2024 On Affine Homotopy between Language Encoders NIPS 2024 From Causal to Concept-Based Representation Learning NIPS 2024 Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents NIPS 2024 Do Finetti: On Causal Effects for Exchangeable Data NIPS 2024 RP1M: A Large-Scale Motion Dataset for Piano Playing with Bi-Manual Dexterous Robot Hands CORL 2024 Moûsai: Efficient Text-to-Music Diffusion Models ACL 2024 Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals ACL 2024 CausalCite: A Causal Formulation of Paper Citations ACL 2024 Benchmarking Offline Reinforcement Learning on Real-Robot Hardware ICLR 2023 Learning Locomotion Skills from MPC in Sensor Space L4DC 2023 BaCaDI: Bayesian Causal Discovery with Unknown Interventions AISTATS 2023 On the Relationship Between Explanation and Prediction: A Causal View ICML 2023 On the Identifiability and Estimation of Causal Location-Scale Noise Models ICML 2023 The Hessian perspective into the Nature of Convolutional Neural Networks ICML 2023 Diffusion Based Representation Learning ICML 2023 Discrete Key-Value Bottleneck ICML 2023 Flow Matching for Scalable Simulation-Based Inference NIPS 2023 Spuriosity Didn’t Kill the Classifier: Using Invariant Predictions to Harness Spurious Features NIPS 2023 Leveraging sparse and shared feature activations for disentangled representation learning NIPS 2023 A Measure-Theoretic Axiomatisation of Causality NIPS 2023 CLadder: Assessing Causal Reasoning in Language Models NIPS 2023 Causal Component Analysis NIPS 2023 Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Data NIPS 2023 Learning Linear Causal Representations from Interventions under General Nonlinear Mixing NIPS 2023 Nonparametric Identifiability of Causal Representations from Unknown Interventions NIPS 2023 SE(3) Equivariant Augmented Coupling Flows NIPS 2023 Controlling Text-to-Image Diffusion by Orthogonal Finetuning NIPS 2023 A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models ACL 2023 Membership Inference Attacks against Language Models via Neighbourhood Comparison ACL 2023 Beyond Good Intentions: Reporting the Research Landscape of NLP for Social Good EMNLP 2023 Homomorphism AutoEncoder -- Learning Group Structured Representations from Observed Transitions ICML 2023 Estimation Beyond Data Reweighting: Kernel Method of Moments ICML 2023 Pairwise Similarity Learning is SimPLE ICCV 2023 Flow Annealed Importance Sampling Bootstrap ICLR 2023 Metrizing Weak Convergence with Maximum Mean Discrepancies JMLR 2023 Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning CLEAR 2023 On the Interventional Kullback-Leibler Divergence CLEAR 2023 Unsupervised Object Learning via Common Fate CLEAR 2023 Provably Learning Object-Centric Representations ICML 2023 Iterative Teaching by Data Hallucination AISTATS 2023 Hindsight States: Blending Sim & Real Task Elements for Efficient Reinforcement Learning RSS 2023 Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels ICML 2023 Causal effect estimation from observational and interventional data through matrix weighted linear estimators UAI 2023 Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap ICLR 2023 DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability ICLR 2023 Structure by Architecture: Structured Representations without Regularization ICLR 2023 Bridging the Gap to Real-World Object-Centric Learning ICLR 2023 On Data Manifolds Entailed by Structural Causal Models ICML 2023 Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers CVPR 2022 Original or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation Performance NAACL 2022 Visual Representation Learning Does Not Generalize Strongly Within the Same Domain ICLR 2022 Phenomenology of Double Descent in Finite-Width Neural Networks ICLR 2022 The Role of Pretrained Representations for the OOD Generalization of RL Agents ICLR 2022 Invariant Causal Representation Learning for Out-of-Distribution Generalization ICLR 2022 Adversarial Robustness Through the Lens of Causality ICLR 2022 You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction ICLR 2022 Group equivariant neural posterior estimation ICLR 2022 Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration ICLR 2022 Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models ICML 2022 Functional Generalized Empirical Likelihood Estimation for Conditional Moment Restrictions ICML 2022 Action-Sufficient State Representation Learning for Control with Structural Constraints ICML 2022 Causal Inference Through the Structural Causal Marginal Problem ICML 2022 On the Adversarial Robustness of Causal Algorithmic Recourse ICML 2022 Generalization and Robustness Implications in Object-Centric Learning ICML 2022 Sampling without Replacement Leads to Faster Rates in Finite-Sum Minimax Optimization NIPS 2022 Assaying Out-Of-Distribution Generalization in Transfer Learning NIPS 2022 Neural Attentive Circuits NIPS 2022 Causal Discovery in Heterogeneous Environments Under the Sparse Mechanism Shift Hypothesis NIPS 2022 Direct Advantage Estimation NIPS 2022 Embrace the Gap: VAEs Perform Independent Mechanism Analysis NIPS 2022 Amortized Inference for Causal Structure Learning NIPS 2022 AutoML Two-Sample Test NIPS 2022 Function Classes for Identifiable Nonlinear Independent Component Analysis NIPS 2022 Probable Domain Generalization via Quantile Risk Minimization NIPS 2022 Exploring the Latent Space of Autoencoders with Interventional Assays NIPS 2022 Interventions, Where and How? Experimental Design for Causal Models at Scale NIPS 2022 When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment NIPS 2022 Learning soft interventions in complex equilibrium systems UAI 2022 On the Fairness of Causal Algorithmic Recourse AAAI 2022 A Learning-based Iterative Control Framework for Controlling a Robot Arm with Pneumatic Artificial Muscles RSS 2022 A Witness Two-Sample Test AISTATS 2022 A prior-based approximate latent Riemannian metric AISTATS 2022 Resampling Base Distributions of Normalizing Flows AISTATS 2022 Adversarially Robust Kernel Smoothing AISTATS 2022 GalilAI: Out-of-Task Distribution Detection using Causal Active Experimentation for Safe Transfer RL AISTATS 2022 Cause-effect inference through spectral independence in linear dynamical systems: theoretical foundations CLEAR 2022 Towards Principled Disentanglement for Domain Generalization CVPR 2022 Towards Total Recall in Industrial Anomaly Detection CVPR 2022 Structural Causal 3D Reconstruction ECCV 2022 Differentially Private Language Models for Secure Data Sharing EMNLP 2022 Logical Fallacy Detection EMNLP 2022 On Disentangled Representations Learned from Correlated Data ICML 2021 Backward-Compatible Prediction Updates: A Probabilistic Approach NIPS 2021 Regret Bounds for Gaussian-Process Optimization in Large Domains NIPS 2021 Dynamic Inference with Neural Interpreters NIPS 2021 The Inductive Bias of Quantum Kernels NIPS 2021 Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style NIPS 2021 Iterative Teaching by Label Synthesis NIPS 2021 Causal Influence Detection for Improving Efficiency in Reinforcement Learning NIPS 2021 DiBS: Differentiable Bayesian Structure Learning NIPS 2021 Independent mechanism analysis, a new concept? NIPS 2021 A Theory of Independent Mechanisms for Extrapolation in Generative Models AAAI 2021 Kernel Distributionally Robust Optimization: Generalized Duality Theorem and Stochastic Approximation AISTATS 2021 Geometrically Enriched Latent Spaces AISTATS 2021 Learning with Hyperspherical Uniformity AISTATS 2021 Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP EMNLP 2021 A teacher-student framework to distill future trajectories ICLR 2021 On the Transfer of Disentangled Representations in Realistic Settings ICLR 2021 CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning ICLR 2021 Spatially Structured Recurrent Modules ICLR 2021 Fast And Slow Learning Of Recurrent Independent Mechanisms ICLR 2021 Learning explanations that are hard to vary ICLR 2021 Predicting Infectiousness for Proactive Contact Tracing ICLR 2021 Recurrent Independent Mechanisms ICLR 2021 Bayesian Quadrature on Riemannian Data Manifolds ICML 2021 Function Contrastive Learning of Transferable Meta-Representations ICML 2021 Necessary and sufficient conditions for causal feature selection in time series with latent common causes ICML 2021 Conditional Distributional Treatment Effect with Kernel Conditional Mean Embeddings and U-Statistic Regression ICML 2021 Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning ICML 2021 Neural Lyapunov Redesign L4DC 2021 Approximate Distributionally Robust Nonlinear Optimization with Application to Model Predictive Control: A Functional Approach L4DC 2021 Causal analysis of Covid-19 Spread in Germany NIPS 2020 Learning Kernel Tests Without Data Splitting NIPS 2020 A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation JMLR 2020 Causal Discovery from Heterogeneous/Nonstationary Data JMLR 2020 From Variational to Deterministic Autoencoders ICLR 2020 Algorithmic recourse under imperfect causal knowledge: a probabilistic approach NIPS 2020 Counterfactuals uncover the modular structure of deep generative models ICLR 2020 Fair Decisions Despite Imperfect Predictions AISTATS 2020 Weakly-Supervised Disentanglement Without Compromises ICML 2020 Disentangling Factors of Variations Using Few Labels ICLR 2020 Bayesian Online Prediction of Change Points UAI 2020 Testing Goodness of Fit of Conditional Density Models with Kernels UAI 2020 ODIN: ODE-Informed Regression for Parameter and State Inference in Time-Continuous Dynamical Systems AAAI 2020 TriFinger: An Open-Source Robot for Learning Dexterity CORL 2020 Relative gradient optimization of the Jacobian term in unsupervised deep learning NIPS 2020 On the design of consequential ranking algorithms UAI 2020 Semi-supervised learning, causality, and the conditional cluster assumption UAI 2020 First-Order Adversarial Vulnerability of Neural Networks and Input Dimension ICML 2019 Selecting causal brain features with a single conditional independence test per feature NIPS 2019 On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset NIPS 2019 The Incomplete Rosetta Stone problem: Identifiability results for Multi-view Nonlinear ICA UAI 2019 Coordinating Users of Shared Facilities via Data-driven Predictive Assistants and Game Theory UAI 2019 Robustifying Independent Component Analysis by Adjusting for Group-Wise Stationary Noise JMLR 2019 AReS and MaRS Adversarial and MMD-Minimizing Regression for SDEs ICML 2019 Kernel Mean Matching for Content Addressability of GANs ICML 2019 Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations ICML 2019 Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness ICML 2019 On the Fairness of Disentangled Representations NIPS 2019 Perceiving the arrow of time in autoregressive motion NIPS 2019 Kernel Stein Tests for Multiple Model Comparison NIPS 2019 Spatio-temporal Transformer Network for Video Restoration ECCV 2018 Kernel Distribution Embeddings: Universal Kernels, Characteristic Kernels and Kernel Metrics on Distributions JMLR 2018 Fidelity-Weighted Learning ICLR 2018 Group Invariance Principles for Causal Generative Models AISTATS 2018 Invariant Models for Causal Transfer Learning JMLR 2018 Differentially Private Database Release via Kernel Mean Embeddings ICML 2018 Detecting non-causal artifacts in multivariate linear regression models ICML 2018 On Matching Pursuit and Coordinate Descent ICML 2018 Learning Independent Causal Mechanisms ICML 2018 Tempered Adversarial Networks ICML 2018 Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models NIPS 2018 Informative Features for Model Comparison NIPS 2018 Learning Blind Motion Deblurring ICCV 2017 Discovering Causal Signals in Images CVPR 2017 Flexible Spatio-Temporal Networks for Video Prediction CVPR 2017 Avoiding Discrimination through Causal Reasoning NIPS 2017 AdaGAN: Boosting Generative Models NIPS 2017 Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning NIPS 2017 Causal Discovery from Nonstationary/Heterogeneous Data: Skeleton Estimation and Orientation Determination IJCAI 2017 EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis ICCV 2017 Online Video Deblurring via Dynamic Temporal Blending Network ICCV 2017 Kernel Mean Shrinkage Estimators JMLR 2016 Distinguishing Cause from Effect Using Observational Data: Methods and Benchmarks JMLR 2016 Minimax Estimation of Maximum Mean Discrepancy with Radial Kernels NIPS 2016 Consistent Kernel Mean Estimation for Functions of Random Variables NIPS 2016 The Arrow of Time in Multivariate Time Series ICML 2016 Domain Adaptation with Conditional Transferable Components ICML 2016 Estimating Diffusion Networks: Recovery Conditions, Sample Complexity and Soft-thresholding Algorithm JMLR 2016 Identification of Time-Dependent Causal Model: A Gaussian Process Treatment IJCAI 2015 Inference of Cause and Effect with Unsupervised Inverse Regression AISTATS 2015 Towards a Learning Theory of Cause-Effect Inference ICML 2015 Removing systematic errors for exoplanet search via latent causes ICML 2015 Semi-Supervised Interpolation in an Anticausal Learning Scenario JMLR 2015 Self-Calibration of Optical Lenses ICCV 2015 Seeing the Arrow of Time CVPR 2014 Towards building a Crowd-Sourced Sky Map AISTATS 2014 Consistency of Causal Inference under the Additive Noise Model ICML 2014 Causal Discovery with Continuous Additive Noise Models JMLR 2014 Kernel Mean Estimation via Spectral Filtering NIPS 2014 Domain Adaptation under Target and Conditional Shift ICML 2013 Statistical analysis of coupled time series with Kernel Cross-Spectral Density operators. NIPS 2013 The Randomized Dependence Coefficient NIPS 2013 Causal Inference on Time Series using Restricted Structural Equation Models NIPS 2013 A Machine Learning Approach for Non-blind Image Deconvolution CVPR 2013 Modeling Information Propagation with Survival Theory ICML 2013 Domain Generalization via Invariant Feature Representation ICML 2013 On a Link Between Kernel Mean Maps and Fraunhofer Diffraction, with an Application to Super-Resolution Beyond the Diffraction Limit CVPR 2013 Probabilistic Modeling of Human Movements for Intention Inference RSS 2012 Learning from Distributions via Support Measure Machines NIPS 2012 Semi-Supervised Domain Adaptation with Non-Parametric Copulas NIPS 2012 A Kernel Two-Sample Test JMLR 2012 The representer theorem for Hilbert spaces: a necessary and sufficient condition NIPS 2012 On Causal Discovery with Cyclic Additive Noise Models NIPS 2011 Recovering Intrinsic Images with a Global Sparsity Prior on Reflectance NIPS 2011 Identifying Cause and Effect on Discrete Data using Additive Noise Models AISTATS 2010 Space-Variant Single-Image Blind Deconvolution for Removing Camera Shake NIPS 2010 Hilbert Space Embeddings and Metrics on Probability Measures JMLR 2010 Switched Latent Force Models for Movement Segmentation NIPS 2010 Probabilistic latent variable models for distinguishing between cause and effect NIPS 2010 Kernel Choice and Classifiability for RKHS Embeddings of Probability Distributions NIPS 2009 Bayesian Experimental Design of Magnetic Resonance Imaging Sequences NIPS 2008 Effects of Stimulus Type and of Error-Correcting Code Design on BCI Speller Performance NIPS 2008 Diffeomorphic Dimensionality Reduction NIPS 2008 Characteristic Kernels on Groups and Semigroups NIPS 2008 An Empirical Analysis of Domain Adaptation Algorithms for Genomic Sequence Analysis NIPS 2008 Nonlinear causal discovery with additive noise models NIPS 2008 An Analysis of Inference with the Universum NIPS 2007 Kernel Measures of Conditional Dependence NIPS 2007 A Kernel Statistical Test of Independence NIPS 2007 A Direct Method for Building Sparse Kernel Learning Algorithms JMLR 2006 Correcting Sample Selection Bias by Unlabeled Data NIPS 2006 Implicit Surfaces with Globally Regularised and Compactly Supported Basis Functions NIPS 2006 Learning with Hypergraphs: Clustering, Classification, and Embedding NIPS 2006 Learning Dense 3D Correspondence NIPS 2006 A Kernel Method for the Two-Sample-Problem NIPS 2006 A Local Learning Approach for Clustering NIPS 2006 A Nonparametric Approach to Bottom-Up Visual Saliency NIPS 2006 Large Scale Multiple Kernel Learning JMLR 2006 Use of the Zero-Norm with Linear Models and Kernel Methods JMLR 2003 Regularized Principal Manifolds JMLR 2001