# PWM: Personalized World Models with Online Reinforcement Learning

arXiv: https://arxiv.org/abs/2610.04920 · HTML: https://mlsanity.com/paper/2610.04920/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video-generation world models and simulators, one of 11 directions in World models.
- Builds on 20 of its 24 references that are in the map.
- First posted on arXiv 4 Oct 2026.

## Placed in

- World models / [Video-generation world models and simulators](https://mlsanity.com/wm/video-generation-world-models-and-simulators/)
- Deep reinforcement learning methods / [RL with diffusion and flow models](https://mlsanity.com/deeprl/rl-with-diffusion-and-flow-models/)

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [DanceGRPO: Unleashing GRPO on Visual Generation](https://mlsanity.com/paper/2505.07818/) (2025)
- [DiffusionNFT: Online Diffusion Reinforcement with Forward Process](https://mlsanity.com/paper/2509.16117/) (2025)
- [GameFactory: Creating New Games with Generative Interactive Videos](https://mlsanity.com/paper/2501.08325/) (2025)
- [Video Diffusion Alignment via Reward Gradients](https://mlsanity.com/paper/2407.08737/) (2024)
- [Yume-1.5: A Text-Controlled Interactive World Generation Model](https://mlsanity.com/paper/2512.22096/) (2025)
- [Yume: An Interactive World Generation Model](https://mlsanity.com/paper/2507.17744/) (2025)
- [EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation](https://mlsanity.com/paper/2411.08380/) (2024)
- [InCrowd-VI: A Realistic Visual-Inertial Dataset for Evaluating SLAM in Indoor Pedestrian-Rich Spaces for Human Navigation](https://mlsanity.com/paper/2411.14358/) (2024)

## Abstract (arXiv)

Pretrained world models can generate diverse environments, yet users often want to explore a particular scene specified by their own video. This requires learning the scene's visual identity while retaining the quality of action-conditioned generation. We introduce Personalized World Models (PWM), a framework for customizing interactive world models from short scene videos through online reinforcement learning. In PWM, the support trajectory and its associated controls provide reward feedback on continuations sampled from the current policy. In the GRPO instantiation, group-relative optimization updates a compact LoRA adapter using a unified reward for scene appearance, visual continuity, and motion, while base-policy anchoring regularizes changes to the pretrained generation prior of a frozen Yume-5B backbone. The same adaptation procedure is applied across real and rendered environments. We also instantiate PWM with DiffusionNFT as an alternative reward-guided optimization method for learning the scene-specific adapter. We also introduce PWM-Bench, comprising 150 customization tasks across Indoor, Outdoor, and Gaming, with paired evaluation on held-out continuations. The GRPO and DiffusionNFT instantiations of PWM improve customization over native Yume in 71.3% and 65.3% of the evaluated scenes, respectively, with positive mean gains across all three domains. For the GRPO instantiation, matched SFT comparisons further demonstrate higher mean customization gains and better mean image-quality scores in every domain, while retaining frame-level visual quality close to the pretrained model.