Libero Goal 1

🚀 Hume-Libero_Goal Model Card

This is a Dual-System Visual-Language-Action model with System-2 thinking, trained on Libero-Goal. It offers innovative solutions in the field of robotics, leveraging advanced visual, language, and action capabilities.

• Paper: https://arxiv.org/abs/2505.21432
• Homepage: https://hume-vla.github.io
• Codebase: 🤖 Hume: A Dual-System VLA with System2 Thinking

📄 License

This project is licensed under the MIT License.

📦 Model Information

🚀 Quick Start

Reproduce Paper Results

If you want to reproduce the results in the paper, follow the instruction.

Direct Model Usage

from hume import HumePolicy
import numpy as np

# load policy
hume = HumePolicy.from_pretrained("/path/to/checkpoints")

# config Test-Time Computing args
hume.init_infer(
    infer_cfg=dict(
        replan_steps=8,
        s2_replan_steps=16,
        s2_candidates_num=5,
        noise_temp_lower_bound=1.0,
        noise_temp_upper_bound=1.0,
        time_temp_lower_bound=0.9,
        time_temp_upper_bound=1.0,
        post_process_action=True,
        device="cuda",
    )
)

# prepare observations
observation = {
    "observation.images.image": np.zeros((1,224,224,3), dtype = np.uint8), # (B, H, W, C)
    "observation.images.wrist_image": np.zeros((1,224,224,3), dtype = np.uint8), # (B, H, W, C)
    "observation.state": np.zeros((1, 7)), # (B, state_dim)
    "task": ["Lift the papper"],
}

# Infer the action
action = hume.infer(observation) # (B, action_dim)

📚 Citation

@article{song2025hume,
  title={Hume: Introducing System-2 Thinking in Visual-Language-Action Model},
  author={Anonimous Authors},
  journal={arXiv preprint arXiv:2505.21432},
  year={2025}
}