Skip to content

EmbodiedCity/Worldscape-MoE.code

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Worldscape-MoE

Worldscape-MoE: A Unified Mixture-of-Experts World Model for Scalable Heterogeneous Action Control

Jianjie Fang1,*, Yongyan Xu1,*, Ziyou Wang1,*, Chen Gao1,*,†, Yuchao Huang1, Zhaolu Wang1, Rongze Tang1, Mingyuan Jia1, Baining Zhao1, Weichen Zhang1, Xin Zhang2, Haisheng Su2, Yu Shang1, Wei Wu2, Xinlei Chen1, Yong Li1,†
1Tsinghua University    2Manifold AI
*Equal contribution.  Corresponding authors.

Project Page Demo Video Model

Code will be released on July 20, 2026. Please stay tuned.

Overview

Worldscape-MoE is a Mixture-of-Experts world model for scalable heterogeneous action control. It unifies multiple control interfaces, including camera trajectories, robot actions, and hand-joint signals, within a shared world-dynamics backbone instead of treating each control modality as an isolated modeling problem.

Built on Diffusion Transformers, Worldscape-MoE combines modality-aware control injection, shared and control-specific experts, and a progressive MoE tuning strategy to absorb heterogeneous action supervision while preserving a shared model of world dynamics. Across locomotion, robotic manipulation, and egocentric hand control, it shows that heterogeneous supervision can improve rather than interfere with individual control capabilities, while supporting out-of-distribution generalization and continual extension to new action modalities.

Demo

Worldscape-MoE Demo

Watch the full demo on YouTube

Code Release

We are preparing the codebase for public release. The training and inference code will be open-sourced on July 20, 2026.

Citation

If you find this project useful, please consider citing:

@misc{fang2026worldscapemoe,
  title        = {Worldscape-MoE: A Unified Mixture-of-Experts World Model for Scalable Heterogeneous Action Control},
  author       = {Fang, Jianjie and Xu, Yongyan and Wang, Ziyou and Gao, Chen and Huang, Yuchao and Wang, Zhaolu and Tang, Rongze and Jia, Mingyuan and Zhao, Baining and Zhang, Weichen and Zhang, Xin and Su, Haisheng and Shang, Yu and Wu, Wei and Chen, Xinlei and Li, Yong},
  year         = {2026},
  note         = {Project page: https://worldscape-moe.com}
}

About

The first MoE-based framework for unified and scalable world modeling.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors