Kun Zhang 0001
206 publications
24 venues
H Index 48
Affiliation
Carnegie Mellon University, Department of Philosophy, Pittsburgh, PA, USAMax Planck Institute for Intelligent Systems, T bingen, Germany
Chinese University of Hong Kong, Hong Kong
Links
| Name | Venue | Year | citations |
|---|---|---|---|
Horizontal and Vertical Federated Causal Structure Learning via Higher-order Cumulants.
|
AAAI | 2026 | 0 |
| Revisiting Differentiable Structure Learning: Inconsistency of L1 Penalty and Beyond.
|
AAAI | 2026 | 0 |
| Identifying Weight-Variant Latent Causal Models.
|
JMLR | 2026 | 0 |
| Reflection-Window Decoding: Text Generation with Selective Refinement.
|
ICML | 2025 | 6 |
| Learning Graph Invariance by Harnessing Spuriosity.
|
ICLR | 2025 | 6 |
| Analytic DAG Constraints for Differentiable DAG Learning.
|
ICLR | 2025 | 6 |
| Learning Vision and Language Concepts for Controllable Image Generation.
|
ICML | 2025 | 1 |
| OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation Triad.
|
CVPR | 2025 | 5 |
| Alignclip: navigating the misalignments for robust vision-language generalization.
|
MLJ | 2025 | 6 |
| Learning Disentangled Representation for Multi-Modal Time-Series Sensing Signals.
|
WWW | 2025 | 7 |
| SmartCLIP: Modular Vision-language Alignment with Identification Guarantees.
|
CVPR | 2025 | 6 |
| Identification of Intermittent Temporal Latent Process.
|
ICLR | 2025 | 2 |
| Latent Variable Causal Discovery under Selection Bias.
|
ICML | 2025 | 2 |
| A General Representation-Based Approach to Multi-Source Domain Adaptation.
|
ICML | 2025 | 0 |
| Causal Representation Learning from General Environments under Nonparametric Mixing.
|
AISTATS | 2025 | 4 |
| Learning Hidden Causal Factors from Psychometrics Data Using Distributional Information.
|
Cognitive Science | 2025 | 0 |
| Permutation-based Rank Test in the Presence of Discretization and Application in Causal Discovery with Mixed Data.
|
ICML | 2025 | 2 |
| Noisy Test-Time Adaptation in Vision-Language Models.
|
ICLR | 2025 | 5 |
| Classifying Treatment Responders: Bounds and Algorithms.
|
KDD | 2025 | 1 |
| Nonparametric Factor Analysis and Beyond.
|
AISTATS | 2025 | 2 |
| When Selection Meets Intervention: Additional Complexities in Causal Discovery.
|
ICLR | 2025 | 6 |
| Type Information-Assisted Self-Supervised Knowledge Graph Denoising.
|
AISTATS | 2025 | 0 |
| Fairness on Principal Stratum: A New Perspective on Counterfactual Fairness.
|
ICML | 2025 | 2 |
| Flow: Modularized Agentic Workflow Automation.
|
ICLR | 2025 | 22 |
| Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning.
|
ICLR | 2025 | 5 |
| Causal Graph Transformer for Treatment Effect Estimation Under Unknown Interference.
|
ICLR | 2025 | 3 |
| On the Identification of Temporal Causal Representation with Instantaneous Dependence.
|
ICLR | 2025 | 8 |
| Identification of Latent Confounders via Investigating the Tensor Ranks of the Nonlinear Observations.
|
ICML | 2025 | 2 |
| A Sample Efficient Conditional Independence Test in the Presence of Discretization.
|
ICML | 2025 | 1 |
| Extracting Rare Dependence Patterns via Adaptive Sample Reweighting.
|
ICML | 2025 | 0 |
| A Robust Method to Discover Causal or Anticausal Relation.
|
ICLR | 2025 | 1 |
| Nonparametric Identification of Latent Concepts.
|
ICML | 2025 | 2 |
| Empowering LLMs with Logical Reasoning: A Comprehensive Survey.
|
IJCAI | 2025 | 0 |
| A Skewness-Based Criterion for Addressing Heteroscedastic Noise in Causal Discovery.
|
ICLR | 2025 | 0 |
| Differentiable Causal Discovery for Latent Hierarchical Causal Models.
|
ICLR | 2025 | 0 |
| Causal Representation Learning from Multimodal Biomedical Observations.
|
ICLR | 2025 | 0 |
| Prompting Fairness: Integrating Causality to Debias Large Language Models.
|
ICLR | 2025 | 0 |
| Identifying Semantic Component for Robust Molecular Property Prediction.
|
TPAMI | 2025 | 0 |
| Optimal Kernel Choice for Score Function-based Causal Discovery.
|
ICML | 2024 | 4 |
| ACAMDA: Improving Data Efficiency in Reinforcement Learning through Guided Counterfactual Data Augmentation.
|
AAAI | 2024 | 11 |
| Detecting and Identifying Selection Structure in Sequential Data.
|
ICML | 2024 | 7 |
| MuGSI: Distilling GNNs with Multi-Granularity Structural Information for Graph Classification.
|
WWW | 2024 | 8 |
| LLCP: Learning Latent Causal Processes for Reasoning-based Video Question Answer.
|
ICLR | 2024 | 5 |
| Identifying Selections for Unsupervised Subtask Discovery.
|
NIPS/NeurIPS | 2024 | 1 |
| Causal Structure Recovery with Latent Variables under Milder Distributional and Graphical Assumptions.
|
ICLR | 2024 | 4 |
| On the Parameter Identifiability of Partially Observed Linear Causal Models.
|
NIPS/NeurIPS | 2024 | 6 |
| CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process.
|
ICML | 2024 | 19 |
| Empowering Graph Invariance Learning with Deep Spurious Infomax.
|
ICML | 2024 | 19 |
| Federated Causal Discovery from Heterogeneous Data.
|
ICLR | 2024 | 15 |
| Discovery of the Hidden World with Large Language Models.
|
NIPS/NeurIPS | 2024 | 14 |
| Structural Estimation of Partially Observed Linear Non-Gaussian Acyclic Model: A Practical Approach with Identifiability.
|
ICLR | 2024 | 6 |
| On Causal Discovery in the Presence of Deterministic Relations.
|
NIPS/NeurIPS | 2024 | 7 |
| Causal Temporal Representation Learning with Nonstationary Sparse Transition.
|
NIPS/NeurIPS | 2024 | 11 |
| Neural Collapse Inspired Feature Alignment for Out-of-Distribution Generalization.
|
NIPS/NeurIPS | 2024 | 9 |
| Score-Based Causal Discovery of Latent Variable Causal Models.
|
ICML | 2024 | 17 |
| Learning Discrete Concepts in Latent Hierarchical Models.
|
NIPS/NeurIPS | 2024 | 15 |
| Gene Regulatory Network Inference in the Presence of Dropouts: a Causal View.
|
ICLR | 2024 | 10 |
| Local Causal Discovery with Linear non-Gaussian Cyclic Models.
|
AISTATS | 2024 | 7 |
| Learning Discrete Latent Variable Structures with Tensor Rank Conditions.
|
NIPS/NeurIPS | 2024 | 2 |
| Identifying Latent State-Transition Processes for Individualized Reinforcement Learning.
|
NIPS/NeurIPS | 2024 | 1 |
| On the Recoverability of Causal Relations from Temporally Aggregated I.I.D. Data.
|
ICML | 2024 | 2 |
| Natural Counterfactuals With Necessary Backtracking.
|
NIPS/NeurIPS | 2024 | 1 |
| Causal Representation Learning from Multiple Distributions: A General Setting.
|
ICML | 2024 | 55 |
| Identification of Causal Structure with Latent Variables Based on Higher Order Cumulants.
|
AAAI | 2024 | 0 |
| S3A: Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment.
|
AAAI | 2024 | 0 |
| Towards Understanding Extrapolation: a Causal Lens.
|
NIPS/NeurIPS | 2024 | 0 |
| A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables.
|
ICLR | 2024 | 0 |
| Identifiable Latent Polynomial Causal Models through the Lens of Change.
|
ICLR | 2024 | 0 |
| Procedural Fairness Through Decoupling Objectionable Data Generating Components.
|
ICLR | 2024 | 0 |
| Transferable Time-Series Forecasting Under Causal Conditional Shift.
|
TPAMI | 2024 | 0 |
| Generalized Independent Noise Condition for Estimating Causal Structure with Latent Variables.
|
JMLR | 2024 | 0 |
| Identifiability and Asymptotics in Learning Homogeneous Linear ODE Systems from Discrete Observations.
|
JMLR | 2024 | 0 |
| Causal-learn: Causal Discovery in Python.
|
JMLR | 2024 | 0 |
| Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer.
|
ICCV | 2023 | 28 |
| Feature Expansion for Graph Neural Networks.
|
ICML | 2023 | 16 |
| Evolving Semantic Prototype Improves Generative Zero-Shot Learning.
|
ICML | 2023 | 31 |
| Unsupervised Sampling Promoting for Stochastic Human Trajectory Prediction.
|
CVPR | 2023 | 40 |
| Understanding Masked Autoencoders via Hierarchical Latent Variable Models.
|
CVPR | 2023 | 48 |
| Causal Discovery with Latent Confounders Based on Higher-Order Cumulants.
|
ICML | 2023 | 20 |
| Identification of Nonlinear Latent Hierarchical Models.
|
NIPS/NeurIPS | 2023 | 28 |
| Which is Better for Learning with Noisy Labels: The Semi-supervised Method or Modeling Label Noise?
|
ICML | 2023 | 14 |
| Generalized Precision Matrix for Scalable Estimation of Nonparametric Markov Networks.
|
ICLR | 2023 | 6 |
| Tier Balancing: Towards Dynamic Fairness over Underlying Causal Factors.
|
ICLR | 2023 | 9 |
| Subspace Identification for Multi-Source Domain Adaptation.
|
NIPS/NeurIPS | 2023 | 54 |
| Multi-domain image generation and translation with identifiability guarantees.
|
ICLR | 2023 | 25 |
| Learning World Models with Identifiable Factorization.
|
NIPS/NeurIPS | 2023 | 20 |
| GAIN: On the Generalization of Instructional Action Understanding.
|
ICLR | 2023 | 4 |
| Improving the Expressiveness of K-hop Message-Passing GNNs by Injecting Contextualized Substructure Information.
|
KDD | 2023 | 18 |
| Temporally Disentangled Representation Learning under Unknown Nonstationarity.
|
NIPS/NeurIPS | 2023 | 22 |
| Generalizing Nonlinear ICA Beyond Structural Sparsity.
|
NIPS/NeurIPS | 2023 | 26 |
| Unpaired Image-to-Image Translation with Shortest Path Regularization.
|
CVPR | 2023 | 45 |
| Model Transferability with Responsive Decision Subjects.
|
ICML | 2023 | 0 |
| Identifiability of Label Noise Transition Matrix.
|
ICML | 2023 | 0 |
| SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model.
|
CVPR | 2023 | 0 |
| Counterfactual Generation with Identifiability Guarantees.
|
NIPS/NeurIPS | 2023 | 0 |
| On the Identifiability of Sparse ICA without Assuming Non-Gaussianity.
|
NIPS/NeurIPS | 2023 | 0 |
| PLOT: Prompt Learning with Optimal Transport for Vision-Language Models.
|
ICLR | 2023 | 0 |
| Calibration Matters: Tackling Maximization Bias in Large-scale Advertising Recommendation Systems.
|
ICLR | 2023 | 0 |
| Causal Balancing for Domain Generalization.
|
ICLR | 2023 | 0 |
| Latent Hierarchical Causal Structure Discovery with Rank Constraints.
|
NIPS/NeurIPS | 2022 | 63 |
| Partial disentanglement for domain adaptation.
|
ICML | 2022 | 77 |
| Independence Testing-Based Approach to Causal Discovery under Measurement Error and Linear Non-Gaussian Models.
|
NIPS/NeurIPS | 2022 | 16 |
| Truncated Matrix Power Iteration for Differentiable DAG Learning.
|
NIPS/NeurIPS | 2022 | 31 |
| Factored Adaptation for Non-Stationary Reinforcement Learning.
|
NIPS/NeurIPS | 2022 | 44 |
| Adversarial Robustness Through the Lens of Causality.
|
ICLR | 2022 | 63 |
| Counterfactual Fairness with Partially Known Causal Graph.
|
NIPS/NeurIPS | 2022 | 25 |
| Unsupervised Image-to-Image Translation with Density Changing Regularization.
|
NIPS/NeurIPS | 2022 | 33 |
| Invariant Action Effect Model for Reinforcement Learning.
|
AAAI | 2022 | 12 |
| Optimal Transport for Causal Discovery.
|
ICLR | 2022 | 24 |
| MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Models.
|
NIPS/NeurIPS | 2022 | 30 |
| Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation.
|
CVPR | 2022 | 29 |
| Alleviating Semantics Distortion in Unsupervised Low-Level Image-to-Image Translation via Structure Consistency Constraint.
|
CVPR | 2022 | 22 |
| Temporally Disentangled Representation Learning.
|
NIPS/NeurIPS | 2022 | 67 |
| Conditional Contrastive Learning with Kernel.
|
ICLR | 2022 | 29 |
| On the Identifiability of Nonlinear ICA: Sparsity and Beyond.
|
NIPS/NeurIPS | 2022 | 86 |
| Residual Similarity Based Conditional Independence Test and Its Application in Causal Discovery.
|
AAAI | 2022 | 22 |
| Causal Discovery in Linear Latent Variable Models Subject to Measurement Error.
|
NIPS/NeurIPS | 2022 | 12 |
| Identification of Linear Latent Variable Model with Arbitrary Distribution.
|
AAAI | 2022 | 24 |
| Identification of Linear Non-Gaussian Latent Hierarchical Structure.
|
ICML | 2022 | 62 |
| Action-Sufficient State Representation Learning for Control with Structural Constraints.
|
ICML | 2022 | 0 |
| On the Convergence of Continuous Constrained Optimization for Structure Learning.
|
AISTATS | 2022 | 0 |
| Towards Federated Bayesian Network Structure Learning with Continuous Optimization.
|
AISTATS | 2022 | 0 |
| Learning Temporally Causal Latent Processes from General Temporal Data.
|
ICLR | 2022 | 0 |
| AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning.
|
ICLR | 2022 | 0 |
| Progressive Open-Domain Response Generation with Multiple Controllable Attributes.
|
IJCAI | 2021 | 11 |
| Unaligned Image-to-Image Translation by Learning to Reweight.
|
ICCV | 2021 | 26 |
| DeepTrader: A Deep Reinforcement Learning Approach for Risk-Return Balanced Portfolio Management with Market Conditions Embedding.
|
AAAI | 2021 | 144 |
| Instance-dependent Label-noise Learning under a Structural Causal Model.
|
NIPS/NeurIPS | 2021 | 92 |
| Identification of Partially Observed Linear Causal Models: Graphical Conditions for the Non-Gaussian and Heterogeneous Cases.
|
NIPS/NeurIPS | 2021 | 54 |
| Testing Independence Between Linear Combinations for Causal Discovery.
|
AAAI | 2021 | 21 |
| Improving Causal Discovery By Optimal Bayesian Network Learning.
|
AAAI | 2021 | 25 |
| Domain Adaptation with Invariant Representation Learning: What Transformations to Learn?
|
NIPS/NeurIPS | 2021 | 0 |
| Reliable Causal Discovery with Improved Exact Search and Weaker Assumptions.
|
NIPS/NeurIPS | 2021 | 0 |
| On the Role of Sparsity and DAG Constraints for Learning Linear DAGs.
|
NIPS/NeurIPS | 2020 | 240 |
| Adaptive Task Sampling for Meta-learning.
|
ECCV | 2020 | 61 |
| How do fair decisions fare in long-term qualification?
|
NIPS/NeurIPS | 2020 | 83 |
| Causal Discovery from Multiple Data Sets with Non-Identical Variable Sets.
|
AAAI | 2020 | 39 |
| A Causal View on Robustness of Neural Networks.
|
NIPS/NeurIPS | 2020 | 96 |
| Generalized Independent Noise Condition for Estimating Latent Variable Causal Graphs.
|
NIPS/NeurIPS | 2020 | 105 |
| Label-Noise Robust Domain Adaptation.
|
ICML | 2020 | 38 |
| Domain Adaptation as a Problem of Inference on Graphical Models.
|
NIPS/NeurIPS | 2020 | 71 |
| Compressed Self-Attention for Deep Metric Learning.
|
AAAI | 2020 | 7 |
| LTF: A Label Transformation Framework for Correcting Label Shift.
|
ICML | 2020 | 40 |
| Characterizing Distribution Equivalence and Structure Learning for Cyclic and Acyclic Directed Graphs.
|
ICML | 2020 | 1 |
| Generative-Discriminative Complementary Learning.
|
AAAI | 2020 | 0 |
| Causal Discovery from Heterogeneous/Nonstationary Data.
|
JMLR | 2020 | 0 |
| Learning Linear Non-Gaussian Causal Models in the Presence of Latent Variables.
|
JMLR | 2020 | 0 |
| Likelihood-Free Overcomplete ICA and Applications In Causal Discovery.
|
NIPS/NeurIPS | 2019 | 9 |
| Triad Constraints for Learning Causal Structure of Latent Variables.
|
NIPS/NeurIPS | 2019 | 74 |
| Learning Disentangled Semantic Representation for Domain Adaptation.
|
IJCAI | 2019 | 149 |
| Twin Auxilary Classifiers GAN.
|
NIPS/NeurIPS | 2019 | 48 |
| Low-Dimensional Density Ratio Estimation for Covariate Shift Correction.
|
AISTATS | 2019 | 23 |
| Data-Driven Approach to Multiple-Source Domain Adaptation.
|
AISTATS | 2019 | 23 |
| Causal Discovery with General Non-Linear Relationships using Non-Linear ICA.
|
UAI | 2019 | 102 |
| On Learning Invariant Representations for Domain Adaptation.
|
ICML | 2019 | 529 |
| Specific and Shared Causal Relation Modeling and Mechanism-Based Clustering.
|
NIPS/NeurIPS | 2019 | 27 |
| PRNet: Outdoor Position Recovery for Heterogenous Telco Data by Deep Neural Network.
|
CIKM | 2019 | 6 |
| Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models.
|
ICML | 2019 | 72 |
| Domain Generalization via Multidomain Discriminant Analysis.
|
UAI | 2019 | 125 |
| Neuropathic Pain Diagnosis Simulator for Causal Discovery Algorithm Evaluation.
|
NIPS/NeurIPS | 2019 | 49 |
| Counting and Sampling from Markov Equivalent DAGs Using Clique Trees.
|
AAAI | 2019 | 0 |
| Causal Discovery with Cascade Nonlinear Additive Noise Model.
|
IJCAI | 2019 | 0 |
| Causal Discovery in the Presence of Missing Data.
|
AISTATS | 2019 | 0 |
| Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping.
|
CVPR | 2019 | 0 |
| Causal Discovery with Linear Non-Gaussian Models under Measurement Error: Structural Identifiability Results.
|
UAI | 2018 | 25 |
| Modeling Dynamic Missingness of Implicit Feedback for Recommendation.
|
NIPS/NeurIPS | 2018 | 65 |
| Generalized Score Functions for Causal Discovery.
|
KDD | 2018 | 180 |
| Multi-domain Causal Structure Learning in Linear Systems.
|
NIPS/NeurIPS | 2018 | 61 |
| Deep Domain Generalization via Conditional Invariant Adversarial Networks.
|
ECCV | 2018 | 795 |
| Causal Discovery from Discrete Data using Hidden Compact Representation.
|
NIPS/NeurIPS | 2018 | 46 |
| Collaborative Filtering With Social Exposure: A Modular Approach to Social Recommendation.
|
AAAI | 2018 | 0 |
| Learning Vector Autoregressive Models With Latent Processes.
|
AAAI | 2018 | 0 |
| Learning Causal Structures Using Regression Invariance.
|
NIPS/NeurIPS | 2017 | 69 |
| Causal Discovery from Nonstationary/Heterogeneous Data: Skeleton Estimation and Orientation Determination.
|
IJCAI | 2017 | 155 |
| Behind Distribution Shift: Mining Driving Forces of Changes and Causal Arrows.
|
ICDM | 2017 | 36 |
| Causal Discovery Using Regression-Based Conditional Independence Tests.
|
AAAI | 2017 | 45 |
| Causal Discovery from Temporally Aggregated Time Series.
|
UAI | 2017 | 64 |
| On the Identifiability and Estimation of Functional Causal Models in the Presence of Outcome-Dependent Selection.
|
UAI | 2016 | 21 |
| Learning Network of Multivariate Hawkes Processes: A Time Series Approach.
|
UAI | 2016 | 65 |
| Domain Adaptation with Conditional Transferable Components.
|
ICML | 2016 | 362 |
| Discovering Temporal Causal Relations from Subsampled Data.
|
ICML | 2015 | 95 |
| Identification of Time-Dependent Causal Model: A Gaussian Process Treatment.
|
IJCAI | 2015 | 46 |
| Multi-Source Domain Adaptation: A Causal View.
|
AAAI | 2015 | 203 |
| Causal Inference by Identification of Vector Autoregressive Processes with Hidden Components.
|
ICML | 2015 | 0 |
| A Permutation-Based Kernel Conditional Independence Test.
|
UAI | 2014 | 133 |
| Nonlinear Causal Discovery for High Dimensional Data: A Kernelized Trace Method.
|
ICDM | 2013 | 17 |
| Domain Adaptation under Target and Conditional Shift.
|
ICML | 2013 | 685 |
| Causal discovery with scale-mixture model for spatiotemporal variance dependencies.
|
NIPS/NeurIPS | 2012 | 6 |
| On causal and anticausal learning.
|
ICML | 2012 | 660 |
| Information-geometric approach to inferring causal directions.
|
Artificial Intelligence | 2012 | 308 |
| Kernel-based Conditional Independence Test and Application in Causal Discovery.
|
UAI | 2011 | 693 |
| A General Linear Non-Gaussian State-Space Model.
|
ACML | 2011 | 17 |
| Testing whether linear equations are causal: A free probability theory approach.
|
UAI | 2011 | 41 |
| Multi-label learning by exploiting label dependency.
|
KDD | 2010 | 469 |
| Estimation of a Structural Vector Autoregression Model Using Non-Gaussianity.
|
JMLR | 2010 | 434 |
| Probabilistic latent variable models for distinguishing between cause and effect.
|
NIPS/NeurIPS | 2010 | 140 |
| Inferring deterministic causal relations.
|
UAI | 2010 | 200 |
| Source Separation and Higher-Order Causal Analysis of MEG and EEG.
|
UAI | 2010 | 21 |
| Invariant Gaussian Process Latent Variable Models and Application in Causal Discovery.
|
UAI | 2010 | 14 |
| Causality Discovery with Additive Disturbances: An Information-Theoretical Perspective.
|
ECML/PKDD | 2009 | 48 |
| On the Identifiability of the Post-Nonlinear Causal Model.
|
UAI | 2009 | 613 |
| Nonlinear independent component analysis with minimal nonlinear distortion.
|
ICML | 2007 | 9 |
| Symbol Recognition with Kernel Density Matching.
|
TPAMI | 2006 | 52 |
| To apply score function difference based ICA algorithms to high-dimensional data.
|
ESANN | 2005 | 0 |
| Practical method for blind inversion of Wiener systems.
|
IJCNN | 2004 | 4 |
| Dimension Reduction Based on Orthogonality - A Decorrelation Method in ICA.
|
ICANN | 2003 | 8 |