-
CanViT: Toward Active-Vision Foundation Models
Paper • 2603.22570 • Published • 11 -
canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02
Image Feature Extraction • Updated • 1.01k • 3 -
canvit/canvitb16-add-vpe-finetune-g128px-s512px-in1k-2026-04-06
Image Classification • Updated • 150 • 1
CanViT
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
CanViT (Canvas Vision Transformer) is a scalable recurrent architecture for the Active-Vision Foundation Model (AVFM) era.
See https://github.com/m2b3/CanViT-PyTorch and CanViT: Toward Active-Vision Foundation Models for more.
-
CanViT: Toward Active-Vision Foundation Models
Paper • 2603.22570 • Published • 11 -
canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02
Image Feature Extraction • Updated • 1.01k • 3 -
canvit/canvitb16-add-vpe-finetune-g128px-s512px-in1k-2026-04-06
Image Classification • Updated • 150 • 1
JAX / Flax NNX checkpoints for CanViT. https://github.com/yberreby/CanViT-NNX
models 6
canvit/canvitb16-add-vpe-finetune-g128px-s512px-in1k-2026-04-06-nnx
Image Classification • Updated
canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02-nnx
Image Feature Extraction • Updated
canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02-mlx
Image Feature Extraction • Updated • 1
canvit/canvitb16-add-vpe-finetune-g128px-s512px-in1k-2026-04-06
Image Classification • Updated • 150 • 1
canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02
Image Feature Extraction • Updated • 1.01k • 3
canvit/canvitb16-add-vpe-pretrain-g128px-s1024px-sa1b-dv3b16-2026-02-26-from-in21k-2026-02-02
Updated • 41
datasets 0
None public yet