Dayi Dong, Maulik Bhatt, Aayushi Shrivastava, Lasse Peters, Negar Mehr
University of California, Berkeley
ALTER stands for Adaptation from Limited demonstrations for Team coordination with Existing-skill Retention. It adapts pretrained diffusion policies to coordinate with other robots while retaining their original independent skills. A trainable residual coordination head corrects a frozen base policy using limited collaborative demonstrations and single-agent replay distilled from the base policy itself.
The project website is published from docs/. The website and supporting
media are preserved alongside the research code in this release branch.
If you find ALTER useful in your research, please cite:
@article{dong2026alter,
title={Residual Denoising Enables Sample-Efficient Multi-Agent Coordination on Demand},
author={Dong, Dayi and Bhatt, Maulik and Shrivastava, Aayushi and Peters, Lasse and Mehr, Negar},
journal={arXiv preprint arXiv:2609.32129},
year={2026},
url={https://arxiv.org/abs/2609.32129}
}The simulation code is available on this release branch. Simulation checkpoints and data are public at ALTER-models and ALTER-data. Original code/checkpoints use Apache-2.0; original datasets use CC BY 4.0. See LICENSE and NOTICE for source scope. Hardware artifacts are deferred. Start with installation, artifact integrity/downloads, simulation workflows, and hardware preparation. Licensing review and Hugging Face publication describe the release scope and verification. Local smoke tests do not reproduce the paper tables.