A VLA that sees in metric 3D via robot-base-frame pointmaps. Checkpoints + RoboCasa/LIBERO data. Code: github.com/DAVIAN-Robotics/PointmapVLA
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning
PHUMA: Physically-Grounded Humanoid Locomotion Dataset
Generators, datasets and pi0.5 policies of DiscoDemo. Page: davian-robotics.github.io/DiscoDemo · Code: github.com/DAVIAN-Robotics/DiscoDemo
-
DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning
Paper • 2610.32093 • Published • 28 -
DAVIAN-Robotics/DiscoDemo-Stage1_RL-PnP_Banana
Reinforcement Learning • Updated • 63 -
DAVIAN-Robotics/DiscoDemo-Stage1_RL-PnP_Banana-alpha0
Reinforcement Learning • Updated • 43 -
DAVIAN-Robotics/DiscoDemo-Stage1_RL-StackCube
Reinforcement Learning • Updated • 38
A VLA that sees in metric 3D via robot-base-frame pointmaps. Checkpoints + RoboCasa/LIBERO data. Code: github.com/DAVIAN-Robotics/PointmapVLA
Generators, datasets and pi0.5 policies of DiscoDemo. Page: davian-robotics.github.io/DiscoDemo · Code: github.com/DAVIAN-Robotics/DiscoDemo
-
DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning
Paper • 2610.32093 • Published • 28 -
DAVIAN-Robotics/DiscoDemo-Stage1_RL-PnP_Banana
Reinforcement Learning • Updated • 63 -
DAVIAN-Robotics/DiscoDemo-Stage1_RL-PnP_Banana-alpha0
Reinforcement Learning • Updated • 43 -
DAVIAN-Robotics/DiscoDemo-Stage1_RL-StackCube
Reinforcement Learning • Updated • 38