Robotics
Safetensors
world-action-models
robotwin

SWAM

SWAM project cover

GitHub codeProject websitearXiv paper

This repository provides the pretrained and RoboTwin posttrained checkpoints for SWAM: Scaling World Action Models with Cross-Modal Alignment.

Model checkpoints

Checkpoint Download directory
Pretrained model pretrain
RoboTwin posttrained model posttrain

The posttrained model is initialized from the pretrained checkpoint and trained on RoboTwin Clean data. Each checkpoint is approximately 27.98 GB and stored as sharded Safetensors.

Download and use

Install the Hugging Face CLI.

pip install -U huggingface_hub

Download the pretrained checkpoint.

hf download FreDERicia/SWAM --include "pretrain/*" --local-dir ./SWAM

Download the RoboTwin posttrained checkpoint.

hf download FreDERicia/SWAM --include "posttrain/*" --local-dir ./SWAM

See the SWAM code repository for training and evaluation entry points. Set the resource paths in your loading configuration to the local files and prepare the required Wan and UMT5 components separately.

Related data

Pretraining data · Posttraining data

Code and citation

Code is available in the SWAM code repository.

If you use these models, please cite the SWAM paper.

@misc{zhou2026swam,
  title = {SWAM: Scaling World Action Models with Cross-Modal Alignment},
  author = {Yu Zhou and Xinyuan Xia and Xuankun Yang and Yinghao Yang and Wendi Chen and Bowen Liu and Jianhan Ma and Weicheng Duan and Jun Lv and Cewu Lu and Yanwei Li},
  year = {2026},
  eprint = {2611.12870},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.12870}
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Video Preview
loading

Datasets used to train FreDERicia/SWAM

Collection including FreDERicia/SWAM

Paper for FreDERicia/SWAM