Binli Luo

Correlation-based Self-Supervision for Few-shot Tabular Learning

Non-Additive Time-Series Forecasting via Cross-Decomposition and Linear Attention

Self-adaptive Retrieval-Augmented Reinforcement Learning for Time Series Forecasting

SEAT: Sparsity Enhanced Attention in the frequency domain for Time Series forecasting

CRRL: Learning Channel-invariant Neural Representations for High-performance Cross-day Decoding

SEAT: Sparsified Enhancements for Attention Mechanisms in Time Series Transformers

TIM: Interpretable Modelling of Complex Temporal Interactions in Multivariate Networks