FasterViT achieves a new SOTA Pareto-front in terms of Top-1 accuracy and throughput without extra training data ! We introduce a new self-attention mechanism, denoted as Hierarchical Attention (HAT), ...

Abstract: Flow matching is a recent framework to train generative models that exhibits impressive empirical performance while being relatively easier to train compared with diffusion-based models.

Background Joint analyses across multiple health datasets can increase statistical power and improve the generalisability of ...

A malicious version of the PyTorch Lightning package published on the Python Package Index (PyPI) delivers a credential-stealing payload targeting browsers, environment files, and cloud services. The ...

In yet another software supply chain attack, threat actors have managed to compromise the popular Python package Lightning to push two malicious versions to conduct credential theft. As of writing, ...