Jiecheng Lu

Free Energy Mixer

ZeroS: Zero‑Sum Linear Attention for Efficient Transformers

In-context Time Series Predictor

Linear Transformers as VAR Models: Aligning Autoregressive Attention Mechanisms with Autoregressive Forecasting

WAVE: Weighted Autoregressive Varying Gate for Time Series Forecasting

Autoregressive Moving-average Attention Mechanism for Time Series Forecasting