pi0 — Stack
ICLR 2027 — Review-only mirror
This repository is an anonymized copy of the ManiGuard resources prepared for peer review.
Citation: If you use these resources in your research, please cite the ManiGuard paper. Full citation details will be provided after the double-blind review period.
ManiGuard main-evaluation checkpoint for stack_retrieve.
Selected training step: 20,750.
Download and evaluate
hf download maniguard-review/pi0-stack --local-dir /path/to/pi0-stack
python -m maniguard.serve.openpi_native --config pi0-base_datagen_v1_stack_joint_2cam_lora --checkpoint /path/to/pi0-stack --port 8000
Normalization assets are under assets/maniguard/, matching the ManiGuard training configuration.
Use the ManiGuard family evaluation configuration for camera and action decoding.
License
The fine-tuned weights derive from a Physical Intelligence openpi base model whose VLM backbone is PaliGemma; use of these weights is therefore subject to the Gemma Terms of Use (including the Gemma Prohibited Use Policy), which downstream users must pass on. The openpi training code and ManiGuard's own contributions are Apache-2.0.