Kun Zhang

Distributional Equivalence in Linear Non-Gaussian Latent-Variable Cyclic Causal Models: Characterization and Learning

Characterization and Learning of Causal Graphs with Latent Confounders and Post-treatment Selection from Interventional Data

Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning

On the Thinking-Language Modeling Gap in Large Language Models

Learning General Causal Structures with Hidden Dynamic Process for Climate Analysis

PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits

Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens

Identification of Causal Relationships in Linear Cyclic Models with Latent Variables

Score-based Greedy Search for Structure Identification of Partially Observed Causal Models

Concept Concentration for Faithful Representation Intervention

Controllable Video Generation with Provable Disentanglement

Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making

Provably Learning Task-Relevant World Representation

$\psi$DAG: Projected Stochastic Approximation Iteration for Linear DAG Structure Learning

Top-K Structure Search with Solution Path

Diverse Dictionary Learning

Identifying Partially Observed Causal Models from Heterogeneous/Nonstationary Data

Independence Test for Linear Non-Gaussian Data and Applications in Causal Discovery

Conditional Independent Component Analysis for Estimating Causal Structure with Latent Variables

From Comparison to Composition: Towards Understanding Machine Cognition of Unseen Categories

Attribute-Guided Image Generation with Causally Disentangled Representation

ParamAgent: Language Agents with Parametric Knowledge

Should Bias be Eliminated? A General Framework to Use Bias for OOD Generalization

Identifiable Interpretation in Generative Models via Causal Minimality

Step-Aware Policy Optimization for Reasoning in Diffusion Large Language Models

Editing by Reconstruction: Background Preservation for Instruction-based Autoregressive Image Editing

Towards Identifiable Latent Additive Noise Models

The Power of Order: Fooling LLMs with Adversarial Table Permutation

REL-RAG: Relation-Aware Retrieval-Augmented Generation for Generalizable Knowledge Graph Question Answering

LeGIT: LLM Guided Intervention Targeting for Online Causal Discovery

Understanding Compositional Generalization via Hierarchical Concept Models

Causal Discovery under Changing Mechanisms: A Unified Graphical Approach

Learning Task-Sufficient World Models via Intervention-Curriculum Co-Design

How Effective is Your Rebuttal? Identifying Causal Models from the OpenReview System

When Selection Meets Intervention: Additional Complexities in Causal Discovery

On the Identification of Temporal Causal Representation with Instantaneous Dependence

$\psi$DAG: Projected Stochastic Approximation Iteration for Linear DAG Structure Learning

Thought Communication in Multiagent Collaboration

Learning Counterfactual Outcomes Under Rank Preservation

Nonparametric Identification of Latent Concepts

Latent Variable Causal Discovery under Selection Bias

Analytic DAG Constraints for Differentiable DAG Learning

The third pillar of causal analysis? A measurement perspective on causal representations

Detecting Generated Images by Fitting Natural Image Distributions

Gene Regulatory Network Inference in the Presence of Selection Bias and Latent Confounders

Practical Kernel Selection for Kernel-based Conditional Independence Test

Towards Identifiability of Hierarchical Temporal Causal Representation Learning

Towards Accurate Time Series Forecasting via Implicit Decoding

Online Time Series Forecasting with Theoretical Guarantees

Learning General Causal Structures with Hidden Dynamic Process for Climate Analysis

Differentiable Causal Discovery for Latent Hierarchical Causal Models

A Robust Method to Discover Causal or Anticausal Relation

A Sample Efficient Conditional Independence Test in the Presence of Discretization

Fairness on Principal Stratum: A New Perspective on Counterfactual Fairness

Identification of Intermittent Temporal Latent Process

A Skewness-Based Criterion for Addressing Heteroscedastic Noise in Causal Discovery

LLM Interpretability with Identifiable Temporal-Instantaneous Representation

Towards Self-Refinement of Vision-Language Models with Triangular Consistency

Flow: Modularized Agentic Workflow Automation

A General Representation-Based Approach to Multi-Source Domain Adaptation

Identification of Latent Confounders via Investigating the Tensor Ranks of the Nonlinear Observations

Permutation-based Rank Test in the Presence of Discretization and Application in Causal Discovery with Mixed Data

Extracting Rare Dependence Patterns via Adaptive Sample Reweighting

Revisiting Differentiable Structure Learning: Inconsistency of $\ell_1$ Penalty and Beyond

Learning Graph Invariance by Harnessing Spuriosity

Noisy Test-Time Adaptation in Vision-Language Models

Causal Graph Transformer for Treatment Effect Estimation Under Unknown Interference

Permutation-based Rank Test in the Presence of Discretization and Application in Causal Discovery with Mixed Data

Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning

On the Identifiability of Nonlinear Representation Learning with General Noise

Causal Representation Learning from Multimodal Biomedical Observations

Identification of Nonparametric Dynamic Causal Model and Latent Process for Climate Analysis

Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning

Provably Learning Concepts by Comparison

A Conditional Independence Test in the Presence of Discretization

Prompting Fairness: Integrating Causality to Debias Large Language Models

Turning Challenges into Opportunities: How Distribution Shifts Enhance Identifiability in Causal Representation Learning

Adjusting Pretrained Backbones for Performativity

EM-DARTS: Preventing Performance Collapse in Differentiable Architecture Search with The Edge Mutation Mechanism

Learning Vision and Language Concepts for Controllable Image Generation

Reflection-Window Decoding: Text Generation with Selective Refinement

$\psi$DAG : Projected Stochastic Approximation Iteration for DAG Structure Learning

On the Language of Thoughts in Large Language Models

Counterfactual Delayed Feedback Learning

Reflection Window: Text Generation with Selective Refinement

Higher-Order Causal Structure Learning with Additive Models

Practical Kernel Learning for Kernel-based Conditional Independent Test

Robust Heterogeneous Treatment Effect Estimation under Covariate Perturbation

Principle Counterfactual Fairness

Learning Identifiable Concepts for Compositional Image Generation

Learning Discrete Latent Models from Discrete Observations

TrendDiff: Decoupling Intrinsic and Measurement Trends for Enhanced Time Series Causal Discovery

Consistency Verification for Detecting AI-Generated Images

Gene Regulatory Network Inference in the Presence of Selection Bias and Latent Confounders

Can Large Language Models Help Experimental Design for Causal Discovery?

Procedural Fairness Through Addressing Social Determinants of Opportunity

Towards Accurate Deep Learning Model Selection: A Calibrated Metric Approach