RynnVLA-Latent pretrains a 4B robot policy on 3D latent actions
A 4B policy pretrained on 745.52M descriptors from 30.1K hours of video posts strong LIBERO, VLABench, and RoboTwin scores.
Stories per day · 30 days
Relatedrobotics4droid1egocentric-video1embodied-ai1flow-matching1imitation-learning1libero1manipulation1skelam1skeleton1video-prediction1vla1wing1world-model1world-models1
3 stories, newest first · one card per story
Stories tagged #latent-actions
SkeLAM splits robot latent actions into skeleton and residual
On DROID, end-effector ADE falls 19.5% and LPIPS 11.1% versus DreamDojo, with zero-shot human-to-robot transfer shown qualitatively.
World Action Learning via Interaction-Centric Spectral Latent Guidance
WING transfers interaction knowledge from egocentric human video to robot policies via spectral latent guidance.