i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images
Stronger Normalization-Free Transformers
-
Vero: An Open RL Recipe for General Visual Reasoning
Paper • 2604.04917 • Published • 34 -
zlab-princeton/Vero-Qwen3T-8B
Image-Text-to-Text • 9B • Updated • 31 • 3 -
zlab-princeton/Vero-Qwen3I-8B
Image-Text-to-Text • 9B • Updated • 18 • 2 -
zlab-princeton/Vero-Qwen25-7B
Image-Text-to-Text • 8B • Updated • 12 • 2
[ICLR 2026] SoFlow: Solution Flow Models for One-Step Generative Modeling.
i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models
-
Vero: An Open RL Recipe for General Visual Reasoning
Paper • 2604.04917 • Published • 34 -
zlab-princeton/Vero-Qwen3T-8B
Image-Text-to-Text • 9B • Updated • 31 • 3 -
zlab-princeton/Vero-Qwen3I-8B
Image-Text-to-Text • 9B • Updated • 18 • 2 -
zlab-princeton/Vero-Qwen25-7B
Image-Text-to-Text • 8B • Updated • 12 • 2
[ICLR 2026] SoFlow: Solution Flow Models for One-Step Generative Modeling.
Model Checkpoints for [CVPR 2026] Stronger Normalization-Free Transformers