AI RESEARCH

Cross-Resolution Attention Network for High-Resolution PM2.5 Prediction

arXiv CS.LG

ArXi:2603.11725v1 Announce Type: cross Vision Transformers have achieved remarkable success in spatio-temporal prediction, but their scalability remains limited for ultra-high-resolution, continent-scale domains required in real-world environmental monitoring. A single European air-quality map at 1 km resolution comprises 29M pixels, far beyond the limits of naive self-attention. We