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.
models 25
canvit/canvitb16-add-vpe-finetune-g128px-s512px-in1k-2026-04-06-nnx
Image Classification • Updated • 31
canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02-nnx
Image Feature Extraction • Updated • 32
canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02-mlx
Image Feature Extraction • Updated • 49
canvit/canvitb16-add-vpe-finetune-g128px-s512px-in1k-2026-04-06
Image Classification • Updated • 249 • 1
canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02
Image Feature Extraction • Updated • 1.13k • 3
canvit/probe-ade20k-40k-s512-c16-in21k
Updated • 13
canvit/probe-ade20k-40k-s512-c8-in21k
Updated • 13
canvit/probe-ade20k-40k-dv3s-512px
Updated • 17
canvit/probe-ade20k-40k-dv3s-384px
Updated • 16
canvit/probe-ade20k-40k-dv3s-256px
Updated • 16
datasets 0
None public yet