LaLa-World scales latent world models with language actions
The paper reports comparable planning to an RAEv2 video baseline at 6 times less training cost.
Stories per day · 30 days
Relatedworld-models2egocentric-video1latent-models1model-predictive-control1robotics1robot-navigation1sim-to-real1
2 stories, newest first · one card per story
Stories tagged #language-conditioning
ScaleNav pretrains language-conditioned robot navigation on internet video
Authors report 86.5% success on adapted Short-Horizon OVON and 94.9% on HabitatGS-LN, then tested a real quadruped.