UIPro-7B_Stage2_Web

UIPro: Unleashing Superior Interaction Capability For GUI Agents

<div align="center">

[💻Code] [🚀Quick Start] [📝Paper]

</div>

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

• Developed by: Brave Group, CASIA
• Model type: Vision-Language Model
• Language(s) (NLP): English
• License: Apache License 2.0
• Finetuned from model: Qwen2-VL-7B-Instruct

Model Sources

HongxinLi/UIPro-7B_Stage2_Web is a GUI agentic model finetuned from Qwen2-VL-7B-Instruct. This model is the web-oriented embodiment of UIPro and capable of solving GUI agent tasks on web scenarios.

<!-- Provide the basic links for the model. -->

• Repository: https://github.com/ZJULiHongxin/UIPro
• Paper: https://arxiv.org/abs/2509.17328

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

First, ensure that the necessary dependencies are installed:

pip install transformers
pip install qwen-vl-utils

Inference code example:

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info

# Default: Load the model on the available device(s)
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "HongxinLi/UIPro-7B_Stage2_Mobile", torch_dtype="auto", device_map="auto"
)
processor = AutoProcessor.from_pretrained("HongxinLi/UIPro-7B_Stage2_Mobile")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "./web_6f93090a-81f6-489e-bb35-1a2838b18c01.png",
            },

            {"type": "text", "text": """Given the Web UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: {task}
Action history: {action_history}

Now, first describe the action intent and then directly plan the next action."""},
        ],
    }
]

Citation

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

BibTeX:

@InProceedings{Li_2025_ICCV,
    author    = {Li, Hongxin and Su, Jingran and Chen, Jingfan and Ju, Zheng and Chen, Yuntao and Li, Qing and Zhang, Zhaoxiang},
    title     = {UIPro: Unleashing Superior Interaction Capability For GUI Agents},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2025},
    pages     = {1613-1623}
}

Framework versions

• PEFT 0.11.1