canvit-active-vision-foundation-model

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 frozen pro…

Independent GitHub snapshot · Automated classification · Original documentation governs