PICA-WAM: Visual Perturbation Invariance via Cross-Appearance Self-Alignment in World Action Models
Paper • 2610.26813 • Published
Checkpoints for PICA-WAM: Visual Perturbation Invariance via Cross-Appearance Self-Alignment in World Action Models (arXiv:2610.26813, project page).
| File | Backbone | Benchmark | Training data |
|---|---|---|---|
internw0_delta/robotwin.pt |
InternW0-Δ, initialized from InternW0-Delta-Base | RoboTwin 2.0, aloha_agilex, 14D joint |
Clean demonstrations only (50 tasks × 50) |
InternW0-Delta-RoboTwin/ in the project repository (bash download_checkpoint.sh, then python -m eval.robotwin.run_robotwin). The model is also packaged as the XPolicyLab PICA_WAM adapter.This is a preview release of one PICA-WAM model; further checkpoints will be added to this repository. The released weights are under the MIT License; base models (Wan2.2, RynnBrain, InternW0-Delta-Base) and the RoboTwin data keep their own licenses.
@misc{zou2026picawamvisualperturbationinvariance,
title={PICA-WAM: Visual Perturbation Invariance via Cross-Appearance Self-Alignment in World Action Models},
author={Yude Zou and Yifei Yao and Guanbo Jiao and Jianming Ma and Guanjie Zheng and Xing Gao},
year={2026},
eprint={2610.26813},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2610.26813},
}