canvit-active-vision-foundation-model

【设计与创意】Establishes Active-Vision Foundation Models (AVFM) as a new problem class and proposes CanViT: a retinotopic ViT backbone with Canvas Attention that decouples thinking (glimpse processing) from memory (scene canvas). Dense latent distillation from DINOv3 enables unsupervised pretraining on 1B random glimpses. Achieves 81.2% ImageNet accuracy with fro…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准