My name is Minghui Liao (廖明辉). I am now a researcher in Huawei. My recent works are mainly on multimodal vision language models.

My Google Scholar Homepage

长期招研究实习生，研究方向为视觉语言多模态、文档智能(多模态)等。有顶会顶刊论文优先；能长期（6个月以上）实习优先。感兴趣的同学可以将简历发送至：liaominghui1<at>huawei.com

News

• TextHawk2 and UI-Hawk are released.

Experience

• Researcher: Huawei, 2021–now
• Visiting Student：Johns Hopkins University, with Professor Alan Yuille (2019.12–2020.12)
• Research Intern：Facebook (2019.5–2019.9)
• Research Intern：Megvii (Face++) (2018.3–2019.3)

Selected publications

• Jiwen Zhang, Yaqi Yu, Minghui Liao, Wentao Li, Jihao Wu, Zhongyu Wei, “Ui-hawk: Unleashing the screen stream understanding for gui agents.” Preprints, manuscript/202408.2137 (2024).

• Ya-Qi Yu, Minghui Liao, Jiwen Zhang, Jihao Wu, “Texthawk2: A large vision-language model excels in bilingual ocr and grounding with 16x fewer tokens.” arXiv preprint arXiv:2410.05261 (2024).

• Ya-Qi Yu, Minghui Liao, Jihao Wu, Yongxin Liao, Xiaoyu Zheng, Wei Zeng. “Texthawk: Exploring efficient fine-grained perception of multimodal large language models.” arXiv preprint arXiv:2404.09204 (2024).

• Xinmiao Yu, et al., “Cross-Lingual Text-Rich Visual Comprehension: An Information Theory Perspective”. AAAI 2025.

• Xudong Xie, et al. “WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling.” arXiv preprint arXiv:2410.05970 (2024).

• Jiwen Zhang, et al. “Android in the zoo: Chain-of-action-thought for gui agents.” EMNLP Findings 2024.

• Hao Wang, Minghui Liao, Zhouyi Xie, Wenyu Liu, Xiang Bai, “Partial Scene Text Retrieval”. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024.

• Mingkun Yang, Minghui Liao, Pu Lu, Jing Wang, Shenggao Zhu, Hualin Luo, Qi Tian, Xiang Bai, “Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition”. ACM MM, 2022. Co-first author

• Minghui Liao, Zhisheng Zou, Zhaoyi Wan, Cong Yao, Xiang Bai, “Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion”. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022. code

• Minghang He, Minghui Liao, Zhibo Yang, Humen Zhong, Jun Tang, Wenqing Cheng, Cong Yao, Yongpan Wang, Xiang Bai, “MOST: A Multi-Oriented Scene Text Detector with Localization Refinement”. CVPR, 2021. Co-first author

• Minghui Liao, Guan Pang, Jing Huang, Tal Hassner, Xiang Bai, “Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting”. ECCV, 2020. code

• Minghui Liao, Zhaoyi Wan, Cong Yao, Kai Chen, Xiang Bai, “Real-time Scene Text Detection with Differentiable Binarization”. AAAI, 2020. oral presentation code

• Minghui Liao, Boyu Song, Minghang He, Shangbang Long, Cong Yao, Xiang Bai, “SynthText3D: Synthesizing Scene Text Images from 3D Virtual Worlds”. SCIS 2020. code and data

• Minghui Liao, Pengyuan Lyu, Minghang He, Cong Yao, Wenhao Wu, Xiang Bai, “Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes”. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) code

• MingKun Yang, Yushuo Guan, Minghui Liao, Xin He, Kaigui Bian, Song Bai, Cong Yao, Xiang Bai, “Symmetry-constrained Rectification Network for Scene Text Recognition”. International Conference on Computer Vision (ICCV), 2019

• Minghui Liao, Jian Zhang, Zhaoyi Wan, Fengming Xie, Jiajun Liang, Pengyuan Lyu, Cong Yao, Xiang Bai, “Scene Text Recognition from Two-Dimensional Perspective”. Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), 2019 oral presentation

• Pengyuan Lyu, Minghui Liao, Cong Yao, Wenhao Wu, Xiang Bai, “Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes”. European Conference on Computer Vision (ECCV), 2018, pp. 67-83. Co-first author code

• Minghui Liao, Zhen Zhu, Baoguang Shi, Gui-song Xia, Xiang Bai, “Rotation-Sensitive Regression for Oriented Scene Text Detection”. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 5909-5918. code

• Minghui Liao, Baoguang Shi, Xiang Bai, “TextBoxes++: A Single-Shot Oriented Scene Text Detector”. IEEE Transactions on Image Processing (TIP), 2018, 27(8): 3676-3690. code

• Minghui Liao, Baoguang Shi, Xiang Bai, Xinggang Wang, Wenyu Liu, “Textboxes: A fast text detector with a single deep neural network”. Thirty-First AAAI Conference on Artificial Intelligence (AAAI), 2017, pp. 4161-4167. oral presentation code

• Yingying Zhu, Minghui Liao, Mingkun Yang, Wenyu Liu, “Cascaded segmentation-detection networks for text-based traffic sign detection”. IEEE transactions on intelligent transportation systems, 2018, 19(1): 209-219.

• Baoguang Shi, Cong Yao, Minghui Liao, Mingkun Yang, Pei Xu, Linyan Cui, Serge Belongie, Shijian Lu, Xiang Bai, “ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)”. 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), IEEE, 2017, 1: 1429-1434.

Achievements and Rewards

• 2022: 中国图象图形学学会优秀博士学位论文奖
• 2021：CSIG自然科学奖一等奖
• 2021: AI华人新星百强
• 2019: National Scholarship for PhD Student
• 2019: VALSE Annual Outstanding Student Paper Award Honorable Mention
• 2018：CCF-CV Scholarship for PhD student
• 2017：National Scholarship for Master Student