• Pair-wise comparison mechanism for improved progressing dense critic accuracy, better recognition of state changes, and each step can be the start of the trajectory.

• Multi-modal capabilities - Supports process tracking, task completion judgment, task description estimation, visual question answering, and even embodied action output, equipped with VLA capabilities.

• Flexible zero-shot and one-shot - in-context capabilities, maintaining excellent performance across entities, scenarios, and tasks.

• Human-task synesthesia - Based on the ego4D human dataset, model understands common tasks and build synesthesia for real-world human tasks and embodied tasks.

• Trajectory quality screening - VLAC can evaluate the collected trajectories and filters out low score trajectories based on the VOC value and mask the action with negative pair-wise score, that is, data with low fluency and quality, improving the effect and efficiency of imitation learning.

Framework & Performance

Details about the model's performance and evaluation metrics can be found in the Homepage.

🛠️ Installation

To install from source:

shell

git clone https://github.com/InternRobotics/VLAC.git
cd VLAC
pip install -e .

Running Environment:

	Range	Recommended	Notes
python	>=3.9	3.10
cuda		cuda12	No need to install if using CPU, NPU, MPS
torch	>=2.0
transformers	>=4.51	4.51.3
peft	>=0.15.2
ms-swift		3.3

🚀 Quick Start

python

from evo_vlac import GAC_model
from evo_vlac.utils.video_tool import compress_video
import os
#Consistent with the web interface, the value and citic rewards of video input can be evaluated.


#assign local model path
model_path="set to your local model path"
#download model form https://huggingface.co/InternRobotics/VLAC

#assign video path and task description
test_video='evo_vlac/examples/videos/pick-bowl-test.mp4'
ref_video='evo_vlac/examples/videos/pick-bowl-ref.mov'
task_description='Put up the bowl and place it back in the white storage box.'

#init model
Critic=GAC_model(tag='critic')
Critic.init_model(model_path=model_path,model_type='internvl2',device_map=f'cuda:0')
Critic.temperature=0.5
Critic.top_k=1
Critic.set_config()
Critic.set_system_prompt()

# transform video
test_video_compressed = os.path.join(os.path.dirname(test_video),"test.mp4")
_,output_fps=compress_video(test_video, test_video_compressed,fps=5)
reference_video_compressed = None
if ref_video:
    reference_video_compressed = os.path.join(os.path.dirname(ref_video),"ref.mp4")
    compress_video(ref_video, reference_video_compressed,fps=5)


# generate Critic results
result_path,value_list,critic_list,done_list = Critic.web_trajectory_critic(
    task_description=task_description,
    main_video_path=test_video_compressed,
    reference_video_path=reference_video_compressed,#if None means no reference video, only use task_description to indicate the task
    batch_num=10,#batch number
    ref_num=6,#image number used in reference video
    think=False,# whether to CoT
    skip=5,#pair-wise step
    rich=False,#whether to output decimal value
    reverse_eval=False,#whether to reverse the evaluation(for VROC evaluation)
    output_path="results",
    fps=float(output_fps),
    frame_skip=True,#whether to skip frames(if false, each frame while be evaluated, cost more time)
    done_flag=False,#whether to out put done value
    in_context_done=False,#whether use reference video to generate done value
    done_threshold=0.9,#done threshold
    video_output=True#whether to output video
)


print("=" * 100)
print(">>>>>>>>>Critic results<<<<<<<<<<")
print(" ")

print(f"result path: {result_path}")
print(f"task description: {task_description}")
print("=" * 50)

print("value_list:")
print(value_list)
print("=" * 50)

print("critic_list:")
print(critic_list)
print("=" * 50)

print("done_list:")
print(done_list)
print("=" * 100)

More examples of

• pair-wise image inputs critic. Please check this example

• vla action generation. Please check this example

• data refinement. Please check this example

For training code, please refer to InternVL2.

🔗 Citation

If you find our work helpful, please cite:

bibtex

@inproceedings{zhanggeneralist,
  title={A Generalist Pair-wise Progress Critic Model for Vision-Language-Action Robots},
  author={Zhang, Qi and Zhai, Shaopeng and Zhang, Shengzhe and Liu, Litao and Zhang, Tianyi and Huang, Fuxian and Zhou, Ming},
  booktitle={Forty-third International Conference on Machine Learning}
}

bibtex

@article{zhai2025vision,
  title={A vision-language-action-critic model for robotic real-world reinforcement learning},
  author={Zhai, Shaopeng and Zhang, Qi and Zhang, Tianyi and Huang, Fuxian and Zhang, Haoran and Zhou, Ming and Zhang, Shengzhe and Liu, Litao and Lin, Sixu and Pang, Jiangmiao},
  journal={arXiv preprint arXiv:2509.15937},
  year={2025}
}

InternRobotics/VLAC

VLAC: A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning

🚀 Interactive Demo & Homepage

VLAC-8B is available now：

VLAC-2B

✨ Key Features

Framework & Performance

🛠️ Installation

🚀 Quick Start

🔗 Citation

🙏 Acknowledgments

InternRobotics/
VLAC