Guangyi Chen

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

PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits

Learning General Causal Structures with Hidden Dynamic Process for Climate Analysis

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

Controllable Video Generation with Provable Disentanglement

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

Identifiable Interpretation in Generative Models via Causal Minimality

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

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

Understanding Compositional Generalization via Hierarchical Concept Models

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

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

On the Identification of Temporal Causal Representation with Instantaneous Dependence

Dimensional Collapse in VQVAEs: Evidence and Remedies

Online Time Series Forecasting with Theoretical Guarantees

Towards Identifiability of Hierarchical Temporal Causal Representation Learning

Learning General Causal Structures with Hidden Dynamic Process for Climate Analysis

Identification of Intermittent Temporal Latent Process

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

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

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

Causal Representation Learning from Multimodal Biomedical Observations

Learning Vision and Language Concepts for Controllable Image Generation

Reflection-Window Decoding: Text Generation with Selective Refinement

Counterfactual Delayed Feedback Learning

Reflection Window: Text Generation with Selective Refinement

Robust Heterogeneous Treatment Effect Estimation under Covariate Perturbation