# When World Models Lie: Adaptive Safety Analysis Under Wrong Imaginations

arXiv: https://arxiv.org/abs/2609.34300 · HTML: https://mlsanity.com/paper/2609.34300/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 13 of its 22 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Placed in

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

## Builds on (most cited first, 13 of 13)

- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners](https://mlsanity.com/paper/2307.01928/) (2023)
- [Gemini Robotics: Bringing AI into the Physical World](https://mlsanity.com/paper/2503.20020/) (2025)
- [Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics](https://mlsanity.com/paper/2501.10100/) (2025)
- [Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysis](https://mlsanity.com/paper/2502.00935/) (2025)
- [Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failures](https://mlsanity.com/paper/2505.00779/) (2025)
- [Foundational World Models Accurately Detect Bimanual Manipulator Failures](https://mlsanity.com/paper/2603.06987/) (2026)
- [How to Train Your Latent Control Barrier Function: Smooth Safety Filtering Under Hard-to-Model Constraints](https://mlsanity.com/paper/2511.18606/) (2025)
- [Feedback World Model Enables Precise Guidance of Diffusion Policy](https://mlsanity.com/paper/2605.15705/) (2026)
- [Hallucination in World Models is Predictable and Preventable](https://mlsanity.com/paper/2606.27326/) (2026)
- [Biased Dreams: Limitations to Epistemic Uncertainty Quantification in Latent Dynamics Models](https://mlsanity.com/paper/2604.25416/) (2026)
- [Safe Control using Learned Safety Filters and Adaptive Conformal Inference](https://mlsanity.com/paper/2604.18482/) (2026)

## Abstract (arXiv)

World models offer a powerful substrate for safety reasoning in high-dimensional robotic systems, but they are also fallible: their predictions can be biased, miscalibrated, or confidently wrong. This creates a central challenge for latent-space safety filters, which often learn Hamilton-Jacobi safety value functions on the dynamics of a world model. If the world model is incorrect, the resulting value function can inherit its errors and produce overconfident safety estimates. Existing latent safety filters often rely on auxiliary signals such as ensemble disagreement or value-target consistency residuals for adaptation, but these signals can remain small even when the world model's predictions deviate from observations. We propose an adaptive latent safety filter that calibrates safety reasoning using directly observed world-model error. Our method uses Adaptive Conformal Inference to construct online uncertainty sets from discrepancies between predicted and observation-inferred latent states, then evaluates safety pessimistically by minimizing the learned value function over these sets. This allows the filter to remain minimally conservative when the world model is accurate, while becoming more cautious when observations reveal model mismatch. We provide a finite-time coverage guarantee for the adaptive uncertainty radius. Through simulation and hardware experiments, we show that our method significantly reduces failures relative to state-of-the-art latent safety filters while preserving task completion.