A developer has released Frost, a deep learning framework written in roughly 1,400 lines of code, built on top of the Neve programming language. The framework includes parallel dataloaders and GPU ker…
A researcher's causal experiments on nanoGPT, ResNet-18, and a diffusion U-Net indicate that neural networks behave as classical stateful dynamical systems, where the same update has different effects…
A new arXiv preprint (2608.14705v1) comparing hyperparameter optimization protocols for deep learning image classifiers found that 5-fold cross-validation reduces absolute performance-estimation error…
Perforated AI released a perforated version of ResNet-18 on Hugging Face that matches ResNet-34's performance while maintaining ResNet-18's smaller size and compute efficiency, using dendritic optimiz…
PageWatch.tech has developed a computer vision diff pipeline for web change monitoring that combines SSIM, ORB feature matching, and a Siamese ResNet-18 neural network to handle layout shifts and dyna…
A new study on arXiv (2607.16231v1) evaluates OrthoGrad, a geometric intervention that removes the radial component of weight gradients during optimizer updates, in noisy-label image classification. O…
AMD ROCm software provides an open-source stack for programming AMD GPUs, enabling high-performance video inference pipelines. A tutorial demonstrates building a pipeline using rocDecode for hardware-…
A new benchmark dataset, Similar-but-Different, from Caleb Robinson and colleagues at Microsoft, shows that most pre-trained geospatial foundation models fail to use non-visible multispectral bands, g…
Researchers introduced Jenga Inverse Predictor (JIP-2), a GPU-accelerated deep learning framework that reconstructs collapsed stone structures by treating anastylosis as an inverse prediction task. Th…
Researchers introduced GRAPE, a training framework that progressively exposes neural network parameters to improve adversarial robustness. On CIFAR-10 with ResNet-18, GRAPE achieved 56.94% PGD-20 robu…