Tag: sparse attention

Researchers have developed an unsupervised deep learning model called GSA-VAE that detects faults in electric vehicle batteries by fusing causal ...

A new dual-branch U-Net called PDSA-DBUNet combines dynamic sparse attention with a polynomial mixer to achieve record abdominal CT segmentation ...

A new transformer-based deep learning framework called RefFree-Phaser achieves genotype phasing accuracies above 91 percent without the large reference panels ...