EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control
Paper • 2508.21112 • Published • 78
EO-Robotics
EmbodiedOneVision is a unified framework for multimodal embodied reasoning and robot control, featuring interleaved vision-text-action pretraining.
-
-
IPEC-COMMUNITY/EO-1-3B
Robotics • 4B • Updated • 423 • 14 -
IPEC-COMMUNITY/EO-Data1.5M
Viewer • Updated • 1.42M • 15.8k • 19 -
IPEC-COMMUNITY/demos25
Viewer • Updated • 75 • 361 -
IPEC-COMMUNITY/eo1-qwen25_vl-bridge
Robotics • 4B • Updated • 79 • 1 -
IPEC-COMMUNITY/eo1-qwen25_vl-fractal
Robotics • 4B • Updated • 14 -
IPEC-COMMUNITY/EO-Bench
Viewer • Updated • 600 • 212 • 2