Improved Baselines with Representation Autoencoders
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Solaris: Building a Multiplayer Video World Model in Minecraft
Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders
Organization Card
Edit this README.md markdown file to author your organization card.
models 48
nyu-visionx/RAEv2-models
Updated • 2
nyu-visionx/Scale-RAE-Qwen1.5B_DiT2.4B-64ep
Text Generation • 4B • Updated • 91
nyu-visionx/Scale-RAE-Qwen7B_DiT9.8B-64ep
Text Generation • 17B • Updated • 6
nyu-visionx/solaris
Updated • 10
nyu-visionx/RAE-mae-base-p16-ViTXL-n08
Updated • 51
nyu-visionx/RAE-siglip2-base-p16-i256-ViTXL-n08
Updated • 45
nyu-visionx/RAE-dinov2-wReg-large-ViTXL-n08
Updated • 35 • 1
nyu-visionx/RAE-dinov2-wReg-small-ViTXL-n08
Updated • 37
nyu-visionx/RAE-dinov2-wReg-base-ViTXL-n08-i512
Updated • 25
nyu-visionx/RAE-dinov2-wReg-base-ViTXL-n08
Updated • 163
datasets 19
nyu-visionx/RAEv2-artifacts
Updated • 22 • 2
nyu-visionx/vpi
Updated • 55
nyu-visionx/solaris-eval-datasets
Viewer • Updated • 1.28k • 1.28k • 1
nyu-visionx/VSI-590K-MetaInfo
Updated • 25
nyu-visionx/proint
Updated • 3
nyu-visionx/solaris-training-dataset
Updated • 256 • 3
nyu-visionx/scale-rae-data
Updated • 5.6k • 3
nyu-visionx/Cambrian-S-3M
Updated • 58.9k • 6
nyu-visionx/VSI-Bench
Viewer • Updated • 10.3k • 10.7k • 65
nyu-visionx/VSI-Train-10k
Viewer • Updated • 10k • 232 • 4