# Bounding Distributional Shifts in World Modeling through Novelty Detection

arXiv: https://arxiv.org/abs/2508.06096 · HTML: https://mlsanity.com/paper/2508.06096/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 8 Aug 2025.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)

## Builds on (most cited first, 23 of 23)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning](https://mlsanity.com/paper/2411.04983/) (2024)
- [Deep Convolutional Inverse Graphics Network](https://mlsanity.com/paper/1503.03167/) (2015)
- [Exploring Model-based Planning with Policy Networks](https://mlsanity.com/paper/1906.08649/) (2019)
- [WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens](https://mlsanity.com/paper/2401.09985/) (2024)
- [Real-Time Anomaly Detection and Reactive Planning with Large Language Models](https://mlsanity.com/paper/2407.08735/) (2024)
- [Learning to Predict Vehicle Trajectories with Model-based Planning](https://mlsanity.com/paper/2103.04027/) (2021)
- [On the role of planning in model-based deep reinforcement learning](https://mlsanity.com/paper/2011.04021/) (2020)
- [Combating the Compounding-Error Problem with a Multi-step Model](https://mlsanity.com/paper/1905.13320/) (2019)
- [Model-Based Visual Planning with Self-Supervised Functional Distances](https://mlsanity.com/paper/2012.15373/) (2020)
- [EVA: An Embodied World Model for Future Video Anticipation](https://mlsanity.com/paper/2410.15461/) (2024)
- [Combining Physics and Deep Learning to learn Continuous-Time Dynamics Models](https://mlsanity.com/paper/2110.01894/) (2021)
- [An Analysis of Frame-skipping in Reinforcement Learning](https://mlsanity.com/paper/2102.03718/) (2021)
- [Optimal Cost Design for Model Predictive Control](https://mlsanity.com/paper/2104.11353/) (2021)
- [Variational Autoencoder for Anomaly Detection: A Comparative Study](https://mlsanity.com/paper/2408.13561/) (2024)
- [Fast Model Identification via Physics Engines for Data-Efficient Policy Search](https://mlsanity.com/paper/1710.08893/) (2017)
- [Enhancing Reconstruction-Based Out-of-Distribution Detection in Brain MRI with Model and Metric Ensembles](https://mlsanity.com/paper/2412.17586/) (2024)

## Built on by (most cited first, 2 of 2)

- [From Generative Engines to Actionable Simulators: The Imperative of Physical Grounding in World Models](https://mlsanity.com/paper/2601.15533/) (2026)
- [Safety, Security, and Cognitive Risks in World Models](https://mlsanity.com/paper/2604.01346/) (2026)

## Abstract (arXiv)

Recent work on visual world models shows significant promise in latent state dynamics obtained from pre-trained image backbones. However, most of the current approaches are sensitive to training quality, requiring near-complete coverage of the action and state space during training to prevent divergence during inference. To make a model-based planning algorithm more robust to the quality of the learned world model, we propose in this work to use a variational autoencoder as a novelty detector to ensure that proposed action trajectories during planning do not cause the learned model to deviate from the training data distribution. To evaluate the effectiveness of this approach, a series of experiments in challenging simulated robot environments was carried out, with the proposed method incorporated into a model-predictive control policy loop extending the DINO-WM architecture. The results clearly show that the proposed method improves over state-of-the-art solutions in terms of data efficiency.