ShowUI: One Vision-Language-Action Model for GUI Visual Agent
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915035817705472 |
|---|---|
| author | Lin, Kevin Qinghong Li, Linjie Gao, Difei Yang, Zhengyuan Wu, Shiwei Bai, Zechen Lei, Weixian Wang, Lijuan Shou, Mike Zheng |
| author_facet | Lin, Kevin Qinghong Li, Linjie Gao, Difei Yang, Zhengyuan Wu, Shiwei Bai, Zechen Lei, Weixian Wang, Lijuan Shou, Mike Zheng |
| contents | Building Graphical User Interface (GUI) assistants holds significant promise for enhancing human workflow productivity. While most agents are language-based, relying on closed-source API with text-rich meta-information (e.g., HTML or accessibility tree), they show limitations in perceiving UI visuals as humans do, highlighting the need for GUI visual agents. In this work, we develop a vision-language-action model in digital world, namely ShowUI, which features the following innovations: (i) UI-Guided Visual Token Selection to reduce computational costs by formulating screenshots as an UI connected graph, adaptively identifying their redundant relationship and serve as the criteria for token selection during self-attention blocks; (ii) Interleaved Vision-Language-Action Streaming that flexibly unifies diverse needs within GUI tasks, enabling effective management of visual-action history in navigation or pairing multi-turn query-action sequences per screenshot to enhance training efficiency; (iii) Small-scale High-quality GUI Instruction-following Datasets by careful data curation and employing a resampling strategy to address significant data type imbalances. With above components, ShowUI, a lightweight 2B model using 256K data, achieves a strong 75.1% accuracy in zero-shot screenshot grounding. Its UI-guided token selection further reduces 33% of redundant visual tokens during training and speeds up the performance by 1.4x. Navigation experiments across web Mind2Web, mobile AITW, and online MiniWob environments further underscore the effectiveness and potential of our model in advancing GUI visual agents. The models are available at https://github.com/showlab/ShowUI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_17465 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ShowUI: One Vision-Language-Action Model for GUI Visual Agent Lin, Kevin Qinghong Li, Linjie Gao, Difei Yang, Zhengyuan Wu, Shiwei Bai, Zechen Lei, Weixian Wang, Lijuan Shou, Mike Zheng Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Human-Computer Interaction Building Graphical User Interface (GUI) assistants holds significant promise for enhancing human workflow productivity. While most agents are language-based, relying on closed-source API with text-rich meta-information (e.g., HTML or accessibility tree), they show limitations in perceiving UI visuals as humans do, highlighting the need for GUI visual agents. In this work, we develop a vision-language-action model in digital world, namely ShowUI, which features the following innovations: (i) UI-Guided Visual Token Selection to reduce computational costs by formulating screenshots as an UI connected graph, adaptively identifying their redundant relationship and serve as the criteria for token selection during self-attention blocks; (ii) Interleaved Vision-Language-Action Streaming that flexibly unifies diverse needs within GUI tasks, enabling effective management of visual-action history in navigation or pairing multi-turn query-action sequences per screenshot to enhance training efficiency; (iii) Small-scale High-quality GUI Instruction-following Datasets by careful data curation and employing a resampling strategy to address significant data type imbalances. With above components, ShowUI, a lightweight 2B model using 256K data, achieves a strong 75.1% accuracy in zero-shot screenshot grounding. Its UI-guided token selection further reduces 33% of redundant visual tokens during training and speeds up the performance by 1.4x. Navigation experiments across web Mind2Web, mobile AITW, and online MiniWob environments further underscore the effectiveness and potential of our model in advancing GUI visual agents. The models are available at https://github.com/showlab/ShowUI. |
| title | ShowUI: One Vision-Language-Action Model for GUI Visual Agent |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Human-Computer Interaction |
| url | https://arxiv.org/abs/2411.17465 |