Towards VLA-Dreamer: Refining VLA Behavior Using World Models

arXiv:2609.31313 · cs.RO, cs.AI · Submitted 2026-09-25 · Read on arXiv

cs.RO, cs.AI

Submitted: 2026-09-25

Updated: 2026-09-25

Terminology

• World Model — 39× in this paper · explained in 7 episodes
• Embeddings — 26× in this paper · explained in 2 episodes
• Reward Function — 3× in this paper · explained in 2 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Accuracy — 2× in this paper · explained in 1 episode
• Fidelity — 2× in this paper · explained in 2 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Sample Efficiency — 2× in this paper · explained in 4 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Sim-to-Real Gap — 1× in this paper · explained in 6 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• VLA Models — 1× in this paper · explained in 3 episodes

Sources

• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• PaliGemma: A versatile 3B VLM for transfer
• SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
• World Action Models are Zero-shot Policies
• DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving