Downloads · 30 days
32
13% of all-time downloads
rhodes-team-teleai/pi05_TACO_libero_finetuned
pi05_TACO_libero_finetuned is a robotics model from rhodes-team-teleai. Use it for the robotics task on the model card, and read the license before you ship it in a product. It is set up for lerobot. The card lists the license as apache-2.0.
[](https://huggingface.co/papers/2512.02834) [](https://vla-anti-exploration.github.io/) [](https://github.com/breez3young/TACO)
Downloads · 30 days
32
13% of all-time downloads
All-time downloads
244
Public
Parameters
3.6B
7.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors7.5 GB · 94%
How the weights are stored.
BF163.5B · 97%
From the Hugging Face model README
This repository contains the pi05 model finetuned on the dataset mixed over LIBERO-Spatial, LIBERO-Goal, LIBERO-Object and LIBERO-Long, together with our trained Coin Flipping Network (CFN), as described in the paper Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach.
TACO (Test-time Anti-exploration via pseudo-COunts) is a novel test-time scaling framework for VLAs which retains the strong generalization capabilities of pretrained VLAs while effectively constraining outputs to the success modes of specific downstream tasks, performing the Anti-Exploration principle in offline RL. By leveraging a lightweight Coin Flipping Network (CFN), TACO acquires accurate measurement of distributional shift with minimal computational overhead, significantly improving performance on out-of-distribution testcases.
Create a conda env:
conda create -n taco python=3.10 -y
conda activate taco
Install torch (choose the version that suits your environment):
pip install torch==2.7.0 torchvision==0.22.0 torchaudio==2.7.0
Install CFN:
cd cfn/
pip install -e .
cd ..
Install Pi0.5 (lerobot):
cd third_party/lerobot
pip install -e .
cd src/transformers
pip install -e .
cd ../../../..
We provide pre-trained base policies and CFN checkpoints on 🤗 Hugging Face, allowing you to directly evaluate TACO without training.
# Download base policy checkpoints & CFN checkpoints
### CFN state dict is saved at `cfns` sub-directory in the repo
hf download rhodes-team-teleai/pi05_TACO_libero_finetuned --local-dir /path/to/your/dir --max-workers 16
For full evaluation and training scripts, please refer to the official GitHub repository.
bash ./scripts/collect_inernal_representation/pi05_libero/collect.sh
bash ./scripts/train_cfn/train_cfn_example.sh
bash ./scripts/eval/eval_libero_pi05_taco.sh
This project is licensed under the Apache License 2.0.
If you find TACO useful for your research, please cite our paper:
@article{yang2025taco,
title={Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach},
author={Siyuan Yang, Yang Zhang, Haoran He, Ling Pan, Xiu Li, Chenjia Bai, Xuelong Li},
journal={arXiv preprint arXiv:2512.02834},
year={2025}
}