Skip to content
arXiv Game World Models & Generation· Zhexin Lou·· 2026-10-04PickAI score41

PWM: customizing personalized world models from short videos with online reinforcement learning

PWM: Personalized World Models with Online Reinforcement Learning

AI summary

The study proposes the PWM (Personalized World Models) framework, which uses online reinforcement learning to customize interactive world models from short videos, training a compact LoRA adapter on a frozen Yume-5B backbone.

Why it matters

The paper presents PWM-Bench's 150 customization tasks and two sets of comparison data for GRPO and DiffusionNFT, which can be used to judge how reproducible scene customization is.

Source: arXiv Game World Models & Generation · arxiv.org