Yujia Zheng

Learning General Causal Structures with Hidden Dynamic Process for Climate Analysis

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

Provably Learning Task-Relevant World Representation

Diverse Dictionary Learning

Top-K Structure Search with Solution Path

Attribute-Guided Image Generation with Causally Disentangled Representation

Provably Learning Representations under Generalized Dependency Structure

ParamAgent: Language Agents with Parametric Knowledge

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

Understanding Catastrophic Interference On the Identifibility of Latent Representations

Thought Communication in Multiagent Collaboration

Nonparametric Identification of Latent Concepts

Learning General Causal Structures with Hidden Dynamic Process for Climate Analysis

Identification of Intermittent Temporal Latent Process

LLM Interpretability with Identifiable Temporal-Instantaneous Representation

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

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

Provably Learning Concepts by Comparison

Learning Vision and Language Concepts for Controllable Image Generation

Higher-Order Causal Structure Learning with Additive Models

Learning Identifiable Concepts for Compositional Image Generation

Learning Discrete Latent Models from Discrete Observations