Zhi Gao | Vision-Language Models | Best Researcher Award

Dr. Zhi Gao | Vision-Language Models | Best Researcher Award

Postdoctoral Research Fellow at Peking University, China.

Dr. Zhi Gao is a Postdoctoral Research Fellow at the School of Intelligence Science and Technology, Peking University. His research focuses on multimodal learning, vision-language models, and human-robot interaction. With expertise in computer vision and machine learning, he explores the development of intelligent agents capable of understanding and interacting with complex environments.

Professional Profile:

Google Scholar Profile

Education Background 🎓📖

  • Ph.D. in Computer Science and Technology, Beijing Institute of Technology (2018–2023)
  • Master in Computer Science and Technology, Beijing Institute of Technology (2017–2018)
  • B.S. in Computer Science and Technology, Beijing Institute of Technology (2013–2017)

Professional Development 📈💡

Dr. Gao is currently a Postdoctoral Research Fellow at Peking University under the supervision of Prof. Song-Chun Zhu, focusing on multimodal learning and agent development. Concurrently, he serves as a Research Scientist at the Beijing Institute for General Artificial Intelligence, working on vision-language models in the Machine Learning Lab. His research integrates deep learning, data representation, and human-centered AI to enhance machine perception and reasoning.

Research Focus 🔬📖

His work spans computer vision and machine learning, particularly in developing multimodal agents capable of learning from human-robot interactions and adapting to dynamic environments. He is also interested in leveraging the geometry of data space to address challenges such as insufficient annotations and distribution shifts.

Author Metrics

  • Publications in top-tier AI and computer vision conferences and journals
  • Research contributions in multimodal intelligence, vision-language understanding, and AI-driven reasoning

Awards & Honors 🏆🎖️

  • National Science Foundation for Young Scientists of China (2025–2027) for research on Riemannian multimodal large language models for video understanding
  • Distinguished Dissertation Award from SIGAI CHINA (October 202X)

Publication Top Notes

1. A Hyperbolic-to-Hyperbolic Graph Convolutional Network

Authors: Jindou Dai, Yuwei Wu, Zhi Gao, Yunde Jia
Published in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 154-163
Abstract: This paper introduces a hyperbolic-to-hyperbolic graph convolutional network (H2H-GCN) that operates directly on hyperbolic manifolds. The proposed method includes a manifold-preserving graph convolution with hyperbolic feature transformation and neighborhood aggregation, avoiding distortions from tangent space approximations. Extensive experiments demonstrate substantial improvements in tasks such as link prediction, node classification, and graph classification.

2. Curvature Generation in Curved Spaces for Few-Shot Learning

Authors: Zhi Gao, Yuwei Wu, Yunde Jia, Mehrtash Harandi
Published in: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 8671-8680
Abstract: This research addresses few-shot learning by proposing task-aware curved embedding spaces using hyperbolic geometry. By generating task-specific embedding spaces with appropriate curvatures, the method enhances the generality of embeddings. The study leverages intra-class and inter-class context information to create discriminative class prototypes, showing benefits over existing embedding methods in both inductive and transductive few-shot learning scenarios.

3. Deep Convolutional Network with Locality and Sparsity Constraints for Texture Classification

Authors: Xiaoyu Bu, Yuwei Wu, Zhi Gao, Yunde Jia
Published in: Pattern Recognition, Volume 91, 2019, Pages 34-46
Abstract: This paper presents a deep convolutional network incorporating locality and sparsity constraints to improve texture classification. The proposed model enhances feature representation by enforcing local connectivity and sparse activation, leading to improved classification performance on texture datasets.

4. Meta-Causal Learning for Single Domain Generalization

Authors: Jianlong Chen, Zhi Gao, Xiaodan Wu, Jiebo Luo
Published in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Abstract: The study introduces a meta-causal learning framework aimed at enhancing generalization in single-domain settings. By leveraging causal relationships within the data, the approach seeks to improve model robustness when applied to unseen domains, addressing challenges in domain generalization.

5. A Robust Distance Measure for Similarity-Based Classification on the SPD Manifold

Authors: Zhi Gao, Yuwei Wu, Mehrtash Harandi, Yunde Jia
Published in: IEEE Transactions on Neural Networks and Learning Systems, Volume 31, Issue 9, 2019, Pages 3230-3244
Abstract: This research proposes a robust distance measure tailored for similarity-based classification tasks on the Symmetric Positive Definite (SPD) manifold. The developed measure enhances classification accuracy by effectively capturing the intrinsic geometry of the SPD manifold, demonstrating robustness in various similarity-based classification scenarios.

Conclusion:

Dr. Zhi Gao is a strong candidate for the Best Researcher Award, given his groundbreaking contributions in vision-language models, hyperbolic learning, and multimodal AI. His strong academic background, top-tier publications, and national recognition make him a well-qualified nominee. However, to further strengthen his impact, he could focus on industry collaborations, real-world AI applications, and global AI leadership.

Verdict:Highly suitable for the Best Researcher Award with minor areas of improvement for long-term impact.

An Zeng | Machine Learning | Best Researcher Award

Prof. An Zeng | Machine Learning | Best Researcher Award

Professor at Guangdong University of Technology, China📖

Professor Zeng An is a distinguished researcher with extensive expertise in machine learning, data mining technologies, and their applications in medicine. Her work has significantly contributed to the advancement of deep learning, neural networks, probabilistic models, rough set theory, genetic algorithms, and other optimization methods. Since her postdoctoral research at the National Research Council of Canada and Dalhousie University (2008–2011) under the guidance of Professor Kenneth Rockwood, Professor Xiaowei Song, and Professor Arnold Mitnitski, she has been dedicated to applying these computational techniques to clinical research on Alzheimer’s Disease (AD).

Profile

Scopus Profile

Education Background🎓

Professor Zeng An completed her postdoctoral research at the National Research Council of Canada, collaborating with leading experts in medical AI applications. She holds a Ph.D. in Computer Science with a focus on machine learning and data mining techniques for medical applications. Her academic journey also includes a master’s and a bachelor’s degree in computer science or related fields (specific institutions and years can be added if available).

Professional Experience🌱

With a career spanning academia and research, Professor Zeng An has held key positions in leading universities and research institutions. During her postdoctoral tenure (2008–2011), she worked at Dalhousie University’s Faculty of Computer Science and Faculty of Medicine, contributing to AI-driven clinical research on neurodegenerative diseases. She has since continued her work in academia, conducting research on advanced machine learning techniques, medical data analysis, and clinical decision support systems.

Research Interests🔬

Professor Zeng An’s research focuses on developing intelligent algorithms for medical applications, particularly in Alzheimer’s Disease diagnostics and prediction. She specializes in deep learning, neural networks, probabilistic models, genetic algorithms, and optimization techniques. Her work extends to clinical data mining, patient risk assessment, and AI-driven medical decision-making, significantly impacting precision medicine.

Author Metrics

Professor Zeng An has a strong publication record in high-impact journals and conferences related to machine learning, AI in healthcare, and medical informatics. Her work has received substantial citations, reflecting her influence in the field. Key metrics such as H-index, i10-index, and total citations further highlight her academic contributions (specific numbers can be added if available).

Awards & Honors

Throughout her career, Professor Zeng An has received prestigious awards and recognitions for her contributions to AI and medical research. Her collaborations with renowned scientists in AI-driven healthcare innovations have led to groundbreaking advancements in the field. She continues to be a leading figure in interdisciplinary research, bridging computer science and medicine for improved healthcare outcomes.

Publications Top Notes 📄

1. Reinforcement Learning-Based Method for Type B Aortic Dissection Localization

  • Authors: Zeng An, Xianyang Lin, Jingliang Zhao, Baoyao Yang, Xin Liu
  • Journal: Journal of Biomedical Engineering (Shengwu Yixue Gongchengxue Zazhi), 2024
  • Citations: 0
  • Summary: This study presents a reinforcement learning-based approach for accurately localizing Type B aortic dissection, improving diagnostic precision in medical imaging.

2. Progressive Deep Snake for Instance Boundary Extraction in Medical Images (Open Access)

  • Authors: Zixuan Tang, Bin Chen, Zeng An, Mengyuan Liu, Shen Zhao
  • Journal: Expert Systems with Applications, 2024
  • Citations: 2
  • Summary: The research introduces a progressive deep snake model to enhance boundary extraction in medical images, facilitating precise segmentation for clinical applications.

3. Multi-Scale Quaternion CNN and BiGRU with Cross Self-Attention Feature Fusion for Fault Diagnosis of Bearing

  • Authors: Huanbai Liu, Fanlong Zhang, Yin Tan, Shenghong Luo, Zeng An
  • Journal: Measurement Science and Technology, 2024
  • Citations: 1
  • Summary: This paper develops a multi-scale quaternion CNN and BiGRU model integrating cross self-attention feature fusion to enhance the accuracy of bearing fault diagnosis in industrial applications.

4. An Ensemble Model for Assisting Early Alzheimer’s Disease Diagnosis Based on Structural Magnetic Resonance Imaging with Dual-Time-Point Fusion

  • Authors: Zeng An, Jianbin Wang, Dan Pan, Wenge Chen, Juhua Wu
  • Journal: Journal of Biomedical Engineering (Shengwu Yixue Gongchengxue Zazhi), 2024
  • Citations: 0
  • Summary: The study proposes an ensemble model utilizing dual-time-point fusion of MRI scans to improve early detection and diagnosis of Alzheimer’s Disease.

5. FedDUS: Lung Tumor Segmentation on CT Images Through Federated Semi-Supervised Learning with Dynamic Update Strategy

  • Authors: Dan Wang, Chu Han, Zhen Zhang, Zhenwei Shi, Zaiyi Liu
  • Journal: Computer Methods and Programs in Biomedicine, 2024
  • Summary: This research introduces a federated semi-supervised learning framework with a dynamic update strategy for effective lung tumor segmentation in CT imaging.

Conclusion

Professor An Zeng is a highly qualified candidate for the Best Researcher Award, given her outstanding contributions to AI in medicine, deep learning, and computational diagnostics. Her strong publication record, international research experience, and interdisciplinary approach make her an excellent nominee. While expanding clinical collaborations and citation impact would further enhance her profile, her cutting-edge research already positions her as a leader in medical AI applications.