# ICAT: Incident-Case-Grounded Adaptive Testing for Physical-Risk Prediction in Embodied World Models

arXiv: https://arxiv.org/abs/2604.16405 · HTML: https://mlsanity.com/paper/2604.16405/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in World models for navigation, one of 11 directions in World models.
- Builds on 54 of its 55 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Placed in

- World models / [World models for navigation](https://mlsanity.com/wm/world-models-for-navigation/)

## Builds on (most cited first, 30 of 54)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [Latte: Latent Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2401.03048/) (2024)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [Lumiere: A Space-Time Diffusion Model for Video Generation](https://mlsanity.com/paper/2401.12945/) (2024)
- [DayDreamer: World Models for Physical Robot Learning](https://mlsanity.com/paper/2206.14176/) (2022)
- [EvalCrafter: Benchmarking and Evaluating Large Video Generation Models](https://mlsanity.com/paper/2310.11440/) (2023)
- [Diffusion for World Modeling: Visual Details Matter in Atari](https://mlsanity.com/paper/2405.12399/) (2024)
- [Open-Sora Plan: Open-Source Large Video Generation Model](https://mlsanity.com/paper/2412.00131/) (2024)
- [SkyReels-V2: Infinite-length Film Generative Model](https://mlsanity.com/paper/2504.13074/) (2025)
- [World Simulation with Video Foundation Models for Physical AI](https://mlsanity.com/paper/2511.00062/) (2025)
- [VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation](https://mlsanity.com/paper/2406.15252/) (2024)
- [T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation](https://mlsanity.com/paper/2407.14505/) (2024)
- [Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation](https://mlsanity.com/paper/2410.05363/) (2024)
- [Human-to-Robot Imitation in the Wild](https://mlsanity.com/paper/2207.09450/) (2022)
- [TransDreamer: Reinforcement Learning with Transformer World Models](https://mlsanity.com/paper/2202.09481/) (2022)
- [Training Agents Inside of Scalable World Models](https://mlsanity.com/paper/2509.24527/) (2025)
- [ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation](https://mlsanity.com/paper/2402.04324/) (2024)
- [GenSim: Generating Robotic Simulation Tasks via Large Language Models](https://mlsanity.com/paper/2310.01361/) (2023)

## Abstract (arXiv)

Video-generative world models are increasingly used as neural simulators for embodied planning and policy learning, yet their ability to predict physical risk and severe consequences is rarely evaluated.We find that these models often downplay or omit key danger cues and severe outcomes for hazardous actions, which can induce unsafe preferences during planning and training on imagined rollouts. We propose ICAT, which grounds testing in real incident reports and safety manuals by building structured risk memories and retrieving/composing them to constrain the generation of risk cases with causal chains and severity labels. Experiments on an ICAT-based benchmark show that mainstream world models frequently miss mechanisms and triggering conditions and miscalibrate severity, falling short of the reliability required for safety-critical embodied deployment.