# Inference-Time Enhancement of Generative Robot Policies via Predictive World Modeling

arXiv: https://arxiv.org/abs/2502.00622 · HTML: https://mlsanity.com/paper/2502.00622/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 35 of its 47 references that are in the map.
- First posted on arXiv 2 Feb 2025.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)
- 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 35)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Learning Universal Policies via Text-Guided Video Generation](https://mlsanity.com/paper/2302.00111/) (2023)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [Evaluating Real-World Robot Manipulation Policies in Simulation](https://mlsanity.com/paper/2405.05941/) (2024)
- [Learning Interactive Real-World Simulators](https://mlsanity.com/paper/2310.06114/) (2023)
- [DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning](https://mlsanity.com/paper/2411.04983/) (2024)
- [Transformers are Sample-Efficient World Models](https://mlsanity.com/paper/2209.00588/) (2022)
- [Diffusion for World Modeling: Visual Details Matter in Atari](https://mlsanity.com/paper/2405.12399/) (2024)
- [Deep Visual Foresight for Planning Robot Motion](https://mlsanity.com/paper/1610.00696/) (2016)
- [Navigation World Models](https://mlsanity.com/paper/2412.03572/) (2024)
- [RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation](https://mlsanity.com/paper/2311.01455/) (2023)
- [Foundation Models in Robotics: Applications, Challenges, and the Future](https://mlsanity.com/paper/2312.07843/) (2023)
- [Action-Conditional Video Prediction using Deep Networks in Atari Games](https://mlsanity.com/paper/1507.08750/) (2015)
- [Learning to Act from Actionless Videos through Dense Correspondences](https://mlsanity.com/paper/2310.08576/) (2023)
- [Video Language Planning](https://mlsanity.com/paper/2310.10625/) (2023)
- [Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Models](https://mlsanity.com/paper/2308.01557/) (2023)
- [Behavior Generation with Latent Actions](https://mlsanity.com/paper/2403.03181/) (2024)
- [Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation](https://mlsanity.com/paper/2409.16283/) (2024)
- [GenSim: Generating Robotic Simulation Tasks via Large Language Models](https://mlsanity.com/paper/2310.01361/) (2023)
- [A Review on Deep Learning Techniques for Video Prediction](https://mlsanity.com/paper/2004.05214/) (2020)
- [Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance](https://mlsanity.com/paper/2410.13816/) (2024)
- [GenAug: Retargeting behaviors to unseen situations via Generative Augmentation](https://mlsanity.com/paper/2302.06671/) (2023)
- [From Imitation to Refinement -- Residual RL for Precise Assembly](https://mlsanity.com/paper/2407.16677/) (2024)
- [Dreamitate: Real-World Visuomotor Policy Learning via Video Generation](https://mlsanity.com/paper/2406.16862/) (2024)
- [Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following](https://mlsanity.com/paper/2402.06559/) (2024)

## Built on by (most cited first, 24 of 24)

- [World Action Models: The Next Frontier in Embodied AI](https://mlsanity.com/paper/2605.12090/) (2026)
- [World Model for Robot Learning: A Comprehensive Survey](https://mlsanity.com/paper/2605.00080/) (2026)
- [World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry](https://mlsanity.com/paper/2604.01985/) (2026)
- [Self-Refining Video Sampling](https://mlsanity.com/paper/2601.18577/) (2026)
- [Masked Visual Actions for Unified World Modeling](https://mlsanity.com/paper/2607.19343/) (2026)
- [FACT: Failure-Aware Causal Training for World-Action Models](https://mlsanity.com/paper/2608.10232/) (2026)
- [World-Action Models for Robot Learning and Control: A Survey](https://mlsanity.com/paper/2609.16074/) (2026)
- [PACT-WAM: Predicting Actions and Visual Foresight with Compact Temporal Encoding for Robot Manipulation](https://mlsanity.com/paper/2602.15882/) (2026)
- [From World Models to World Action Models: A Concise Tutorial for Robotics](https://mlsanity.com/paper/2607.00836/) (2026)
- [DriftWorld: Fast World Modeling through Drifting](https://mlsanity.com/paper/2607.15065/) (2026)
- [World Models for Robotic Manipulation: A Survey](https://mlsanity.com/paper/2606.00113/) (2026)
- [Structured 4D Latent Predictive Model for Robot Planning](https://mlsanity.com/paper/2607.01166/) (2026)
- [Robot Self-Improvement via Human-Video Dynamics Models](https://mlsanity.com/paper/2606.21406/) (2026)
- [ICPRL: Acquiring Physical Intuition from Interactive Control](https://mlsanity.com/paper/2603.13295/) (2026)
- [Cortex 2.0: Grounding World Models in Real-World Industrial Deployment](https://mlsanity.com/paper/2604.20246/) (2026)
- [DreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA Policies](https://mlsanity.com/paper/2605.11750/) (2026)
- [PhysCoRe: Physics-Corrected Residual World Models for Material-Aware Deformable Dynamics](https://mlsanity.com/paper/2607.20653/) (2026)
- [SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators](https://mlsanity.com/paper/2609.09155/) (2026)
- [Data-Asymmetric Latent Imagination and Reranking for 3D Robotic Imitation Learning](https://mlsanity.com/paper/2605.10166/) (2026)
- [ReGuide: From Test-Time Guidance to Self-Improving Diffusion Policies](https://mlsanity.com/paper/2606.28939/) (2026)
- [CereVLA: Cerebellum-Inspired Consequence-Aware Residual Governance for Efficient Vision-Language-Action Execution](https://mlsanity.com/paper/2609.27468/) (2026)
- [Robot Learning with Visual Predicted Force](https://mlsanity.com/paper/2610.04741/) (2026)
- [LeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPC](https://mlsanity.com/paper/2610.12407/) (2026)
- [Dream to Remember: Continual Steering of Generalist Robot Policies with World Models](https://mlsanity.com/paper/2610.13816/) (2026)

## Abstract (arXiv)

We present Generative Predictive Control (GPC), an inference-time method for improving pretrained behavior-cloning policies without retraining. GPC augments a frozen diffusion policy at deployment with an action-conditioned world model trained on expert demonstrations and random exploration rollouts. The world model predicts the consequences of action proposals generated by the diffusion policy and enables lightweight online planning that ranks and refines these proposals through model-based look-ahead. By combining a generative prior with predictive foresight, GPC enables test-time adaptation while keeping the original policy fixed. Across diverse robotic manipulation tasks, including state- and vision-based settings in both simulation and real-world experiments, GPC consistently outperforms standard behavior cloning and compares favorably with other inference-time adaptation baselines.