نسخة أولية وصول مفتوح
Random Feature Gaussian Process Attention: Linear-Time Probabilistic Attention with Calibrated Uncertainty
Transformers provide a state-of-the-art modeling framework, yet poor calibration limits their reliability in safety-critical applications. A promising direction addresses this issue by interpreting attention as a Gaussian process (GP) posterior, which enables principled uncertainty calibration but incurs cubic complexi …