# Toward Stable World Models: Measuring and Addressing World Instability in Generative Environments

arXiv: https://arxiv.org/abs/2503.08122 · HTML: https://mlsanity.com/paper/2503.08122/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Video-generation world models and simulators, one of 11 directions in World models.
- Builds on 33 of its 41 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Placed in

- World models / [Video-generation world models and simulators](https://mlsanity.com/wm/video-generation-world-models-and-simulators/)

## Builds on (most cited first, 30 of 33)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [Diffusion for World Modeling: Visual Details Matter in Atari](https://mlsanity.com/paper/2405.12399/) (2024)
- [Diffusion Models Are Real-Time Game Engines](https://mlsanity.com/paper/2408.14837/) (2024)
- [StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text](https://mlsanity.com/paper/2403.14773/) (2024)
- [World Model on Million-Length Video And Language With Blockwise RingAttention](https://mlsanity.com/paper/2402.08268/) (2024)
- [Structured World Models from Human Videos](https://mlsanity.com/paper/2308.10901/) (2023)
- [Transformer-based World Models Are Happy With 100k Interactions](https://mlsanity.com/paper/2303.07109/) (2023)
- [GameGen-X: Interactive Open-world Game Video Generation](https://mlsanity.com/paper/2411.00769/) (2024)
- [MEt3R: Measuring Multi-View Consistency in Generated Images](https://mlsanity.com/paper/2501.06336/) (2025)
- [STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning](https://mlsanity.com/paper/2310.09615/) (2023)
- [Learning to Simulate Dynamic Environments with GameGAN](https://mlsanity.com/paper/2005.12126/) (2020)
- [On the Content Bias in Fr'echet Video Distance](https://mlsanity.com/paper/2404.12391/) (2024)
- [Counter-Strike Deathmatch with Large-Scale Behavioural Cloning](https://mlsanity.com/paper/2104.04258/) (2021)
- [Temporally Consistent Transformers for Video Generation](https://mlsanity.com/paper/2210.02396/) (2022)
- [RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences](https://mlsanity.com/paper/2402.17257/) (2024)
- [Exploring the Training Robustness of Distributional Reinforcement Learning against Noisy State Observations](https://mlsanity.com/paper/2109.08776/) (2021)

## Built on by (most cited first, 5 of 5)

- [DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving](https://mlsanity.com/paper/2601.01528/) (2026)
- [StateSpaceDiffuser: Bringing Long Context to Diffusion World Models](https://mlsanity.com/paper/2505.22246/) (2025)
- [Out of Sight, Out of Mind? Evaluating State Evolution in Video World Models](https://mlsanity.com/paper/2603.13215/) (2026)
- [A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and Platform](https://mlsanity.com/paper/2610.00926/) (2026)
- [Kuration SDK: Addressing the Virtual2Real Gap via Data Curation](https://mlsanity.com/paper/2610.09305/) (2026)

## Abstract (arXiv)

We present a novel study on enhancing the capability of preserving the content in world models, focusing on a property we term World Stability. Recent diffusion-based generative models have advanced the synthesis of immersive and realistic environments that are pivotal for applications such as reinforcement learning and interactive game engines. However, while these models excel in quality and diversity, they often neglect the preservation of previously generated scenes over time--a shortfall that can introduce noise into agent learning and compromise performance in safety-critical settings. In this work, we introduce an evaluation framework that measures world stability by having world models perform a sequence of actions followed by their inverses to return to their initial viewpoint, thereby quantifying the consistency between the starting and ending observations. Our comprehensive assessment of state-of-the-art diffusion-based world models reveals significant challenges in achieving high world stability. Moreover, we investigate several improvement strategies to enhance world stability. Our results underscore the importance of world stability in world modeling and provide actionable insights for future research in this domain.