5 citations · 6 across the 7 of their papers we have counts for
Showing 2026 · cs.LGShow all
3 papers · 2 filters
cs.LG2026
LLN: Learnable Lens Networks for Parameter-Efficient Long-Horizon Dynamical Prediction
Binbin Yong, Zhao Su, Lan Guo +3
Explicit residual connections of the form (x+f(x)), often combined with normalization layers, have become a standard strategy for training very deep neural networks. However, resid…
cs.LG2026
Fuzzy-MoE: Interpretable Regime-Conditioned Expert Routing for Non-Stationary Multivariate Time Series Forecasting
Lan Guo, Jie Xiao, Zhao Su +5
In non-stationary multivariate time series, different variables and samples often exhibit heterogeneous latent dynamic states, while existing deep forecasting models usually compre…
cs.LG2026
HYDRA: Hyperbolic Dynamic Representation Architecture for Kolmogorov-Arnold Networks
Zhao Su, Yuxin Xia, Haoran Li +4
Kolmogorov-Arnold Networks (KANs) enhance nonlinear function approximation by replacing scalar weights with learnable univariate functions. However, assigning an independent functi…