AINeutralarXiv – CS AI · 18h ago5/10
🧠
PRISM: PRior-guided Imagination Sampling in world Models
PRISM is a new framework for world model-based planning that uses a lightweight neural network to extract action priors from the same dataset and model representations, improving robotic control performance by 32-35 percentage points without additional architectural complexity. The method integrates state-conditioned confidence into sampling distributions through a closed-form probabilistic update, enabling more effective candidate action generation.