Think Like a World Model, Act Like a VLA: Distilling World-Model Representations into Compact Robot Policies
cs.RO, cs.CV
Submitted: 2026-09-21
Updated: 2026-09-22
Code: https://github.com/Lifelong-Robot-Learning/LIBERO
Project page: https://thaw-vla.trung-dt.com
Terminology
Sources
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- Do World Action Models Generalize Better than VLAs? A Robustness Study
- World Action Models are Zero-shot Policies
- Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
- Causal World Modeling for Robot Control
- PaliGemma: A versatile 3B VLM for transfer
- StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
- SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
- VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Models
- Wan: Open and Advanced Large-Scale Video Generative Models
- DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
- Cosmos 3: Omnimodal World Models for Physical AI
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- WorldVLA: Towards Autoregressive Action World Model
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
- OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation
- Light-WAM: Efficient World Action Models with State-Fusion Action Decoding
- Distilling the Knowledge in a Neural Network
- Qwen3-VL Technical Report
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