Open X-Embodiment datasets in LeRobot format with standard transfomation (https://github.com/Tavish9/any4lerobot)
AI & ML interests
Embodied AI
Recent Activity
View all activity
EmbodiedOneVision is a unified framework for multimodal embodied reasoning and robot control, featuring interleaved vision-text-action pretraining.
-
SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model
Paper • 2501.15830 • Published • 13 -
IPEC-COMMUNITY/spatialvla-4b-224-pt
Image-Text-to-Text • 4B • Updated • 5.64k • 14 -
IPEC-COMMUNITY/spatialvla-4b-mix-224-pt
Image-Text-to-Text • 4B • Updated • 17 • 4 -
IPEC-COMMUNITY/spatialvla-4b-224-sft-bridge
Robotics • 4B • Updated • 336 • 2
-
IPEC-COMMUNITY/libero_spatial_no_noops_1.0.0_lerobot
Viewer • Updated • 53k • 4.09k • 4 -
IPEC-COMMUNITY/libero_goal_no_noops_1.0.0_lerobot
Viewer • Updated • 52k • 3.39k • 1 -
IPEC-COMMUNITY/libero_object_no_noops_1.0.0_lerobot
Viewer • Updated • 67k • 3.28k • 1 -
IPEC-COMMUNITY/libero_10_no_noops_1.0.0_lerobot
Viewer • Updated • 101k • 3.84k • 3
Open X-Embodiment datasets in LeRobot format with standard transfomation (https://github.com/Tavish9/any4lerobot)
-
SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model
Paper • 2501.15830 • Published • 13 -
IPEC-COMMUNITY/spatialvla-4b-224-pt
Image-Text-to-Text • 4B • Updated • 5.64k • 14 -
IPEC-COMMUNITY/spatialvla-4b-mix-224-pt
Image-Text-to-Text • 4B • Updated • 17 • 4 -
IPEC-COMMUNITY/spatialvla-4b-224-sft-bridge
Robotics • 4B • Updated • 336 • 2
EmbodiedOneVision is a unified framework for multimodal embodied reasoning and robot control, featuring interleaved vision-text-action pretraining.
-
IPEC-COMMUNITY/libero_spatial_no_noops_1.0.0_lerobot
Viewer • Updated • 53k • 4.09k • 4 -
IPEC-COMMUNITY/libero_goal_no_noops_1.0.0_lerobot
Viewer • Updated • 52k • 3.39k • 1 -
IPEC-COMMUNITY/libero_object_no_noops_1.0.0_lerobot
Viewer • Updated • 67k • 3.28k • 1 -
IPEC-COMMUNITY/libero_10_no_noops_1.0.0_lerobot
Viewer • Updated • 101k • 3.84k • 3