CanViT

community

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

yberreby updated a collection about 17 hours ago

Viewpoint-Q ADE20K glimpse policies

yberreby updated a collection about 17 hours ago

Viewpoint-Q ADE20K glimpse policies

yberreby updated a collection about 17 hours ago

Viewpoint-Q ADE20K glimpse policies

View all activity

Papers

CanViT: Toward Active-Vision Foundation Models

View all Papers

canvit 's collections 8

Viewpoint-Q ADE20K glimpse policies

Learned viewing policies for a frozen CanViT. 2026-07-04 qband: 8 seeds; flagship = s2. Code: github.com/m2b3/CanViT-PyTorch-RL

canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s0

Reinforcement Learning • 5.68M • Updated about 16 hours ago
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s1

Reinforcement Learning • 5.68M • Updated about 16 hours ago
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s2

Reinforcement Learning • 5.68M • Updated about 16 hours ago
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s3

Reinforcement Learning • 5.68M • Updated about 16 hours ago

DINOv3 ADE20K Segmentation Probes (PyTorch)

canvit/probe-ade20k-40k-dv3b-128px

Image Segmentation • 118k • Updated Apr 14 • 2
canvit/probe-ade20k-40k-dv3b-144px

Image Segmentation • 118k • Updated Apr 14 • 2
canvit/probe-ade20k-40k-dv3b-160px

Image Segmentation • 118k • Updated Apr 14 • 2
canvit/probe-ade20k-40k-dv3b-192px

Image Segmentation • 118k • Updated Apr 14 • 2

CanViT (PyTorch)

CanViT: Toward Active-Vision Foundation Models

Paper • 2603.22570 • Published Mar 23 • 13
canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02

Image Feature Extraction • 98.1M • Updated Mar 26 • 1.37k • 3
canvit/canvitb16-add-vpe-finetune-g128px-s512px-in1k-2026-04-06

Image Classification • 95.9M • Updated Apr 7 • 32 • 1
canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in1k-dv3b16-2026-06-22

Image Feature Extraction • 98.1M • Updated 13 days ago • 115

CanViT (MLX)

canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02-mlx

Image Feature Extraction • 98.1M • Updated Apr 7 • 7

CanViT Pretraining Ablations (PyTorch)

Ablation checkpoints for the CanViT pretraining ablation study (appendix).

canvit/canvitb16-abl-baseline-2026-03-02

98.1M • Updated May 1 • 18
canvit/canvitb16-abl-dcan256-2026-03-02

90.4M • Updated May 1 • 14
canvit/canvitb16-abl-no-bptt-2026-03-06

98.1M • Updated May 1 • 15
canvit/canvitb16-abl-no-dense-2026-03-02

98.1M • Updated May 1 • 15

CanViT ADE20K Segmentation Probes (PyTorch)

Linear segmentation probes trained on frozen CanViT canvas features for ADE20K semantic segmentation (150 classes).

canvit/probe-ade20k-40k-s512-c8-in21k

Image Segmentation • 160k • Updated Apr 14 • 7
canvit/probe-ade20k-40k-s512-c9-in21k

Image Segmentation • 160k • Updated Apr 14 • 7
canvit/probe-ade20k-40k-s512-c10-in21k

Image Segmentation • 160k • Updated Apr 14 • 4
canvit/probe-ade20k-40k-s512-c12-in21k

Image Segmentation • 160k • Updated Apr 14 • 6

CanViT (JAX / Flax NNX)

JAX / Flax NNX checkpoints for CanViT. https://github.com/yberreby/CanViT-NNX

canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02-nnx

Image Feature Extraction • 95.2M • Updated Apr 7 • 2
canvit/canvitb16-add-vpe-finetune-g128px-s512px-in1k-2026-04-06-nnx

Image Classification • 96M • Updated Apr 7 • 3

DINOv3 ImageNet-1k Probes (PyTorch)

Linear IN1k classification probes for DINOv3 ViT backbones @ 512x512.

canvit/dinov3-vits16-lvd1689m-in1k-512x512-linear-clf-probe

385k • Updated Apr 25 • 21
canvit/dinov3-vits16plus-lvd1689m-in1k-512x512-linear-clf-probe

385k • Updated Apr 25 • 123
canvit/dinov3-vitb16-lvd1689m-in1k-512x512-linear-clf-probe

769k • Updated Apr 25 • 3.5k
canvit/dinov3-vitl16-lvd1689m-in1k-512x512-linear-clf-probe

1.03M • Updated Apr 25 • 496

Viewpoint-Q ADE20K glimpse policies

Learned viewing policies for a frozen CanViT. 2026-07-04 qband: 8 seeds; flagship = s2. Code: github.com/m2b3/CanViT-PyTorch-RL

canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s0

Reinforcement Learning • 5.68M • Updated about 16 hours ago
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s1

Reinforcement Learning • 5.68M • Updated about 16 hours ago
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s2

Reinforcement Learning • 5.68M • Updated about 16 hours ago
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s3

Reinforcement Learning • 5.68M • Updated about 16 hours ago

CanViT Pretraining Ablations (PyTorch)

Ablation checkpoints for the CanViT pretraining ablation study (appendix).

canvit/canvitb16-abl-baseline-2026-03-02

98.1M • Updated May 1 • 18
canvit/canvitb16-abl-dcan256-2026-03-02

90.4M • Updated May 1 • 14
canvit/canvitb16-abl-no-bptt-2026-03-06

98.1M • Updated May 1 • 15
canvit/canvitb16-abl-no-dense-2026-03-02

98.1M • Updated May 1 • 15

DINOv3 ADE20K Segmentation Probes (PyTorch)

canvit/probe-ade20k-40k-dv3b-128px

Image Segmentation • 118k • Updated Apr 14 • 2
canvit/probe-ade20k-40k-dv3b-144px

Image Segmentation • 118k • Updated Apr 14 • 2
canvit/probe-ade20k-40k-dv3b-160px

Image Segmentation • 118k • Updated Apr 14 • 2
canvit/probe-ade20k-40k-dv3b-192px

Image Segmentation • 118k • Updated Apr 14 • 2

CanViT ADE20K Segmentation Probes (PyTorch)

Linear segmentation probes trained on frozen CanViT canvas features for ADE20K semantic segmentation (150 classes).

canvit/probe-ade20k-40k-s512-c8-in21k

Image Segmentation • 160k • Updated Apr 14 • 7
canvit/probe-ade20k-40k-s512-c9-in21k

Image Segmentation • 160k • Updated Apr 14 • 7
canvit/probe-ade20k-40k-s512-c10-in21k

Image Segmentation • 160k • Updated Apr 14 • 4
canvit/probe-ade20k-40k-s512-c12-in21k

Image Segmentation • 160k • Updated Apr 14 • 6

CanViT (PyTorch)

CanViT: Toward Active-Vision Foundation Models

Paper • 2603.22570 • Published Mar 23 • 13
canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02

Image Feature Extraction • 98.1M • Updated Mar 26 • 1.37k • 3
canvit/canvitb16-add-vpe-finetune-g128px-s512px-in1k-2026-04-06

Image Classification • 95.9M • Updated Apr 7 • 32 • 1
canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in1k-dv3b16-2026-06-22

Image Feature Extraction • 98.1M • Updated 13 days ago • 115

CanViT (JAX / Flax NNX)

JAX / Flax NNX checkpoints for CanViT. https://github.com/yberreby/CanViT-NNX

canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02-nnx

Image Feature Extraction • 95.2M • Updated Apr 7 • 2
canvit/canvitb16-add-vpe-finetune-g128px-s512px-in1k-2026-04-06-nnx

Image Classification • 96M • Updated Apr 7 • 3

CanViT (MLX)

canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02-mlx

Image Feature Extraction • 98.1M • Updated Apr 7 • 7

DINOv3 ImageNet-1k Probes (PyTorch)

Linear IN1k classification probes for DINOv3 ViT backbones @ 512x512.

canvit/dinov3-vits16-lvd1689m-in1k-512x512-linear-clf-probe

385k • Updated Apr 25 • 21
canvit/dinov3-vits16plus-lvd1689m-in1k-512x512-linear-clf-probe

385k • Updated Apr 25 • 123
canvit/dinov3-vitb16-lvd1689m-in1k-512x512-linear-clf-probe

769k • Updated Apr 25 • 3.5k
canvit/dinov3-vitl16-lvd1689m-in1k-512x512-linear-clf-probe

1.03M • Updated Apr 25 • 496

AI & ML interests

Recent Activity

Papers

Team members 4

canvit 's collections 8