N. Le

Time series models can achieve state-of-the-art long-term forecasting by dynamically blending recent dynamics with retrieved historical trajectories, rather than relying solely on a single look-back window.

Recurrently folding older time series context onto a most-recent anchor dramatically improves forecasting accuracy by naturally prioritizing recent evidence.

Ditch the attention: ConvRec proves convolutional networks can beat Transformers in sequential recommendation while slashing compute and memory costs.