Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ODEWorld

[📄 Paper]   [🌐 Website]   [🤗 Hugging Face]

The Official Implementation of "ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow"

Quick Start

Installation

  1. Clone this repository and create the environment.
git clone https://github.com/Dstate/ODEWorld.git
cd ODEWorld
conda create -n odeworld python=3.10 -y
conda activate odeworld
  1. Install the remaining dependencies.
pip install torch==2.6.0 torchvision==0.21.0 torchaudio==2.6.0 --index-url https://download.pytorch.org/whl/cu124
pip install -r requirements.txt
  1. Download the pretrained checkpoints into assets/pretrained.
mkdir -p assets/pretrained

for model in \
  ODEWorld-PT-Flow-LIBERO \
  ODEWorld-PT-Flow-AgiBot \
  ODEWorld-Goal-Predictor-LIBERO \
  ODEWorld-RAE-LIBERO \
  ODEWorld-RAE-AgiBot
do
  hf download "ldxxx/${model}" --local-dir "assets/pretrained/${model}"
done

Demo Inference

Run the LIBERO examples:

python demo_infer.py --dataset libero

Run the AgiBot examples:

python demo_infer.py --dataset agibot

Use --case-ids case_00 to run a single case. Results are written to outputs/<dataset>/<case_id>.

Reference

@article{liu-niu2026odeworld,
  title={ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow},
  author={Liu, Dongxiu and Niu, Haoyi and Cheng, Peng and Gao, Yuan and Kang, Xirui and Teng, Sangli and Sreenath, Koushil and Zhan, Xianyuan},
  journal={arXiv preprint arXiv:2607.27924},
  year={2026}
}

About

The Official Implementation of "ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow"

Resources

Stars

33 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages