---
license: apache-2.0
pipeline_tag: robotics
library_name: transformers
tags:
- vla
- world-model
- embodied-ai
---

# Chain of World: World Model Thinking in Latent Motion

This repository contains the weights for **CoWVLA** (Chain-of-World VLA), a Vision-Language-Action framework that unifies world-model temporal reasoning with disentangled latent motion modeling.

[**🌐 Project Page**](https://fx-hit.github.io/cowvla-io/) | [**📄 Paper**](https://huggingface.co/papers/2603.03195) | [**💻 GitHub**](https://github.com/fx-hit/CoWVLA)

## Overview

CoWVLA introduces a "Chain of World" paradigm to address limitations in current VLA models. While world-model VLAs often waste capacity reconstructing redundant backgrounds and latent-action VLAs lack temporally continuous modeling, CoWVLA:
- Uses a pretrained video VAE (**VidTwin**) to disentangle structure and motion latents.
- Pre-trains a VLA decoder to infer a continuous latent motion chain from an instruction and initial frame.
- Co-fine-tunes the model to align latent dynamics with discrete action prediction in a single autoregressive decoder.

This design preserves the temporal reasoning benefits of world models while maintaining the compactness and interpretability of latent actions.

## Evaluation Results

CoWVLA demonstrates strong performance across major robotic simulation benchmarks:

| Benchmark | Metric | CoWVLA |
| --- | --- | --- |
| **LIBERO** | Spatial / Object / Goal / Long / Avg. | 97.2 / 97.8 / 94.6 / 92.8 / 95.6 |
| **SimplerEnv-WidowX** | Stack / Carrot / Spoon / Eggplant / Avg. | 62.5 / 66.7 / 79.2 / 95.8 / 76.0 |

## Citation

If you find this work useful for your research, please cite:

```bibtex
@inproceedings{yang2026cowvla,
  title     = {Chain of World: World Model Thinking in Latent Motion},
  author    = {Yang, Fuxiang and Di, Donglin and Tang, Lulu and Zhang, Xuancheng and Fan, Lei and Li, Hao and Chen, Wei and Su, Tonghua and Ma, Baorui},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year      = {2026}
}
```