Grounded World Model: Latent Planning with Language Goals
The episode discusses the paper "Grounded World Model: Latent Planning with Language Goals," which proposes using a Grounded World Model (GWM) to enhance Model Predictive Control (MPC) planning. The hosts analyze how tying action selection to high-level linguistic instructions via a vision-language latent space shifts planning from visual matching to semantic goal prediction, leading to improved success rates on complex tasks.