DreamX repurposes video diffusion models as universal latent action learners
DreamX extracts 300x compressed latent actions from pretrained video diffusion models, enabling any-to-any video transfer and zero-shot action transfer across embodiments.
Stories per day · 30 days
Relatedreinforcement-learning2embodiment-transfer1inverse-kinematics1latent-actions1video-diffusion1vision-language-action1
2 stories, newest first · one card per story
Stories tagged #robot-arms
PolicyIK provides high-precision inverse kinematics via reinforcement learning
PolicyIK uses goal-conditioned RL to achieve millimeter-precision IK for robot arms, outperforming classical controllers and enabling 95.7% success in simulated pick-and-place with π0.5.