2 papers
cs.LG2026
Predicting Covariate-Driven Spatial Deformation for Nonstationary Gaussian Processes
Minghao Gu, Weizhi Lin, Qiang Huang
Nonstationary Gaussian processes (GPs) are essential for modeling complex, locally heterogeneous spatial data. A common modeling approach is the spatial deformation method that war…
cs.LG2026
VeFA: Vector-Based Feature Space Adaptation for Robust Model Fine-Tuning
Peng Wang, Minghao Gu, Qiang Huang
Catastrophic forgetting is a well-documented challenge in model fine-tuning, particularly when the downstream domain has limited labeled data or differs substantially from the pre-…