Tag: computational efficiency

A new classifier called CABLE-kNN caches local neighborhood evidence during training and neutralizes class priors, beating ordinary kNN on imbalanced ...

Researchers have developed an evidential deep learning framework that detects stroke with near-perfect accuracy while quantifying its own uncertainty in ...

Researchers have shown that Kriging meta-models can reassess the fatigue lifetime of offshore wind turbines using less than 0.5 percent ...

Researchers have unveiled byteification, a two-stage conversion method that retrofits existing subword-based large language models into byte-level models matching their ...

Researchers at Shahid Chamran University of Ahvaz have built a compact EfficientNet-inspired neural network that classifies music genres from spectrogram ...

A 50-year RegCM5 simulation over the Yellow River Basin shows that the new Moloch non-hydrostatic core reduces wind speed bias ...

A large-scale study finds that pretraining tabular self-supervised models on carefully selected subsets of 100 to 1000 unlabeled examples often ...

A new survey in Artificial Intelligence Review maps the state of multimodal video diffusion models, reporting up to 523-fold computational ...

Researchers in China have developed REF-VMUNetUp, a Mamba-based network with rotary position embeddings and dynamic upsampling that improves multi-organ segmentation ...