# Dreaming the Unseen: World Model-regularized Diffusion Policy for Out-of-Distribution Robustness

arXiv: https://arxiv.org/abs/2603.21017 · HTML: https://mlsanity.com/paper/2603.21017/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in World models for navigation, one of 11 directions in World models.
- Builds on 49 of its 54 references that are in the map.
- First posted on arXiv 22 Mar 2026.

## Placed in

- World models / [World models for navigation](https://mlsanity.com/wm/world-models-for-navigation/)
- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 30 of 49)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects](https://mlsanity.com/paper/2312.08344/) (2023)
- [WorldVLA: Towards Autoregressive Action World Model](https://mlsanity.com/paper/2506.21539/) (2025)
- [Diffusion for World Modeling: Visual Details Matter in Atari](https://mlsanity.com/paper/2405.12399/) (2024)
- [Masked World Models for Visual Control](https://mlsanity.com/paper/2206.14244/) (2022)
- [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024)
- [Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation](https://mlsanity.com/paper/2503.02881/) (2025)
- [Denoising diffusion models for out-of-distribution detection](https://mlsanity.com/paper/2211.07740/) (2022)
- [FlowPolicy: Enabling Fast and Robust 3D Flow-based Policy via Consistency Flow Matching for Robot Manipulation](https://mlsanity.com/paper/2412.04987/) (2024)
- [Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation](https://mlsanity.com/paper/2403.03890/) (2024)
- [Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits](https://mlsanity.com/paper/2411.18704/) (2024)
- [Diffusion Reward: Learning Rewards via Conditional Video Diffusion](https://mlsanity.com/paper/2312.14134/) (2023)
- [Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling](https://mlsanity.com/paper/2408.17355/) (2024)
- [DynaGuide: Steering Diffusion Polices with Active Dynamic Guidance](https://mlsanity.com/paper/2506.13922/) (2025)
- [Diffusion Policies for Out-of-Distribution Generalization in Offline Reinforcement Learning](https://mlsanity.com/paper/2307.04726/) (2023)
- [AffordDP: Generalizable Diffusion Policy with Transferable Affordance](https://mlsanity.com/paper/2412.03142/) (2024)
- [Diffusion Meets DAgger: Supercharging Eye-in-hand Imitation Learning](https://mlsanity.com/paper/2402.17768/) (2024)

## Built on by (most cited first, 3 of 3)

- [World Action Models: A Survey](https://mlsanity.com/paper/2606.20781/) (2026)
- [Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses](https://mlsanity.com/paper/2605.02900/) (2026)
- [Staircase Policy: Streaming Inference for World-Action Models with Large Action Chunks](https://mlsanity.com/paper/2609.36471/) (2026)

## Abstract (arXiv)

Diffusion policies excel at visuomotor control but often fail catastrophically under severe out-of-distribution (OOD) disturbances, such as unexpected object displacements or visual corruptions. To address this vulnerability, we introduce the Dream Diffusion Policy (DDP), a framework that deeply integrates a diffusion world model into the policy's training objective via a shared 3D visual encoder. This co-optimization endows the policy with robust state-prediction capabilities. When encountering sudden OOD anomalies during inference, DDP detects the real-imagination discrepancy and actively abandons the corrupted visual stream. Instead, it relies on its internal "imagination" (autoregressively forecasted latent dynamics) to safely bypass the disruption, generating imagined trajectories before smoothly realigning with physical reality. Extensive evaluations demonstrate DDP's exceptional resilience. Notably, DDP achieves a 73.8% OOD success rate on MetaWorld (vs. 23.9% without predictive imagination) and an 83.3% success rate under severe real-world spatial shifts (vs. 3.3% without predictive imagination). Furthermore, as a stress test, DDP maintains a 76.7% real-world success rate even when relying entirely on open-loop imagination post-initialization.