Yan Liu

PINFDiT: Energy-Based Physics-Informed Diffusion Transformers for General-purpose Time Series Tasks

Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning

Learning What Matters: Toward Causally-Grounded Foundations for Contextual Time-Series Forecasting

Conversational Time Series Foundation Models: Towards Explainable and Effective Forecasting

Informative Posterior Ensembles for Sequential Simulation-Based Inference

When Does Multimodality Lead to Better Time Series Forecasting?

When LLM Meets Time Series: A Real-World Benchmark for Explicit and Implicit Multi-Step Reasoning

Revisiting Feature Interaction Selection in Neural Additive Models

When Splitting Makes Stronger: A Theoretical and Empirical Analysis of Divide-and-Conquer Prompting in LLMs

A Large-scale Dataset and Benchmark for Commuting Origin-Destination Flow Generation

InstaSHAP: Interpretable Additive Models Explain Shapley Values Instantly

TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model

An Examination on the Effectiveness of Divide-and-Conquer Prompting in Large Language Models

Higher-Order Causal Structure Learning with Additive Models

Beyond Forecasting: Compositional Time Series Reasoning for End-to-End Task Execution