# DREAM: Deployment-Time Demonstration Generation via Real-to-Sim for Scalable Policy Adaptation

arXiv: https://arxiv.org/abs/2608.29078 · HTML: https://mlsanity.com/paper/2608.29078/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning and post-training, one of 13 directions in Vision-language-action models.
- Builds on 33 of its 36 references that are in the map.
- First posted on arXiv 29 Aug 2026.

## Placed in

- Vision-language-action models / [Reinforcement learning and post-training](https://mlsanity.com/vla/reinforcement-learning-and-post-training/)

## Builds on (most cited first, 30 of 33)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics](https://mlsanity.com/paper/2506.01844/) (2025)
- [Evaluating Real-World Robot Manipulation Policies in Simulation](https://mlsanity.com/paper/2405.05941/) (2024)
- [RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots](https://mlsanity.com/paper/2406.02523/) (2024)
- [MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations](https://mlsanity.com/paper/2310.17596/) (2023)
- [Integrated Task and Motion Planning](https://mlsanity.com/paper/2010.01083/) (2020)
- [gsplat: An Open-Source Library for Gaussian Splatting](https://mlsanity.com/paper/2409.06765/) (2024)
- [Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition](https://mlsanity.com/paper/2307.14535/) (2023)
- [Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation](https://mlsanity.com/paper/2403.03949/) (2024)
- [DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning](https://mlsanity.com/paper/2410.24185/) (2024)
- [LeRobot: An Open-Source Library for End-to-End Robot Learning](https://mlsanity.com/paper/2602.22818/) (2026)
- [SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splatting](https://mlsanity.com/paper/2409.10161/) (2024)
- [DemoGen: Synthetic Demonstration Generation for Data-Efficient Visuomotor Policy Learning](https://mlsanity.com/paper/2502.16932/) (2025)
- [Imitating Task and Motion Planning with Visuomotor Transformers](https://mlsanity.com/paper/2305.16309/) (2023)
- [cuRobo: Parallelized Collision-Free Minimum-Jerk Robot Motion Generation](https://mlsanity.com/paper/2310.17274/) (2023)
- [SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment](https://mlsanity.com/paper/2410.18907/) (2024)
- [MolmoAct2: Action Reasoning Models for Real-world Deployment](https://mlsanity.com/paper/2605.02881/) (2026)
- [Novel Demonstration Generation with Gaussian Splatting Enables Robust One-Shot Manipulation](https://mlsanity.com/paper/2504.13175/) (2025)
- [Real2Render2Real: Scaling Robot Data Without Dynamics Simulation or Robot Hardware](https://mlsanity.com/paper/2505.09601/) (2025)
- [PolaRiS: Scalable Real-to-Sim Evaluations for Generalist Robot Policies](https://mlsanity.com/paper/2512.16881/) (2025)
- [GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training](https://mlsanity.com/paper/2507.13097/) (2025)
- [Human-in-the-Loop Task and Motion Planning for Imitation Learning](https://mlsanity.com/paper/2310.16014/) (2023)
- [GSWorld: Closed-Loop Photo-Realistic Simulation Suite for Robotic Manipulation](https://mlsanity.com/paper/2510.20813/) (2025)
- [High-Fidelity Simulated Data Generation for Real-World Zero-Shot Robotic Manipulation Learning with Gaussian Splatting](https://mlsanity.com/paper/2510.10637/) (2025)
- [Should We Learn Contact-Rich Manipulation Policies from Sampling-Based Planners?](https://mlsanity.com/paper/2412.09743/) (2024)
- [NOD-TAMP: Generalizable Long-Horizon Planning with Neural Object Descriptors](https://mlsanity.com/paper/2311.01530/) (2023)

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

- [DATAFARM: Distribution-Aligned Task and Motion Planning for Fine-Tuning Vision-Language-Action Models](https://mlsanity.com/paper/2609.12316/) (2026)
- [Splat2Act: From Captured Scenes to Personalized VLA Manipulation](https://mlsanity.com/paper/2610.13945/) (2026)

## Abstract (arXiv)

Vision-language-action (VLA) models have made strong progress in language-conditioned robot manipulation, but improving their performance in a new workspace still often requires action-labeled data from that environment. Collecting such data by human teleoperation is costly, especially when each workspace, object arrangement, or task may require new demonstrations. We present DREAM, a framework that generates fine-tuning data for a pretrained VLA from a captured workspace and a language instruction, without requiring a task-specific human demonstration. DREAM reconstructs the workspace, automatically translates the instruction into symbolic task goals and success criteria using a large language model, and uses task-and-motion planning to generate feasible robot trajectories. The planned trajectories are augmented across randomized object configurations, verified by the generated success criteria, and rendered into image-action examples for VLA fine-tuning. Through real-robot experiments on language-conditioned manipulation tasks, we study whether DREAM can serve as a scalable data-collection system for the deployment workspace by examining whether fine-tuning on its automatically generated data improves success over direct deployment and how its data-collection cost compares with human teleoperation when adapting a VLA to a new workspace.