PCWorld tested the Acer Swift Go 16 AI featuring AMD's new Ryzen AI 7 445 processor, which delivers strong performance and runs quietly under load. The laptop demonstrates midrange performance comparable to Intel's Meteor Lake but suffers significant performance drops when unplugged from power. This Ryzen AI 400 series chip represents AMD's focus on steady, reliable computing rather than flashy features, though 3D graphics capabilities remain limited. I'm just going to say it: 2026 is the most exciting year for productivity laptops ever. I've been covering the chip market dating back to the winter of 1994.

Earth observation foundation models have shown strong generalization across multiple Earth observation tasks, but their robustness under real-world perturbations remains underexplored. To bridge this gap, we introduce REOBench, the first comprehensive benchmark for evaluating the robustness of Earth observation foundation models across six tasks and twelve types of image corruptions, including both appearance-based and geometric perturbations. To ensure realistic and fine-grained evaluation, our benchmark focuses on high-resolution optical remote sensing images, which are widely used in critical applications such as urban planning and disaster response. We conduct a systematic evaluation of a broad range of models trained using masked image modeling, contrastive learning, and vision-language pre-training paradigms. Our results reveal that existing Earth observation foundation models experience significant performance degradation when exposed to input corruptions. The severity of degradation varies across tasks, model architectures, backbone sizes, and types of corruption, with performance drop varying from less than 1% to over 25%. Vision-language models show enhanced robustness, particularly in multimodal tasks. REOBench underscores the vulnerability of current Earth observation foundation models to real-world corruptions and provides actionable insights for developing more robust and reliable models. Code and data are publicly available at https://github.com/lx709/REOBench.

ObjectNet is the same size as the ImageNet test set (50,000 images), and by design does not comepaired withatraining setinordertoencourage generalization.

However,thecompression only in the spatial domain suffers from a dramatic performance drop without finetuning and is not robust to noise, as the noise in the spatial domain can easily confuse the pruning criteria, leading to some parameters/channels being pruned incorrectly.