[{'Paper': 'Towards Identifiability of Hierarchical Temporal Causal Representation Learning', 'Conference': 'NeurIPS 2025'}, {'Paper': 'Online Time Series Forecasting with Theoretical Guarantees', 'Conference': 'NeurIPS 2025'}, {'Paper': 'Learning General Causal Structures with Hidden Dynamic Process for Climate Analysis', 'Conference': 'NeurIPS 2025 CauScien Workshop'}, {'Paper': 'Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making', 'Conference': 'NeurIPS 2025 EWMDM Workshop'}, {'Paper': 'PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits', 'Preprint': 'arXiv'}]
Background
Research interests include inverting observation-generation to unveil the hidden world and how such a hidden world instructs the observed world evolving in response to the environment. Master's thesis can be found here.