Wen Ye

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

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

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

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