PhD Candidate at Tsinghua University, China .
Jingge Wang is a Ph.D. student in Computer Science at Tsinghua University, under the supervision of Prof. Yang Li. He focuses on robust machine learning, generative models, and medical image analysis. Jingge has published in leading journals and conferences such as IEEE JSTSP, MICCAI, and the Journal of the Franklin Institute. He has collaborated internationally, including a visiting research stint at the University of Texas at Austin with Prof. Qixing Huang. His research contributions emphasize generalization in unseen domains and progression-aware medical imaging, showing high innovation and societal relevance. With an exceptional academic record and growing impact, Jingge Wang is highly deserving of the Best Researcher Award, demonstrating both technical depth and practical application in AI for healthcare.
🌍 Professional Profile:
Scopus
Orcid
Google scholar
🏆 Suitability for the Best Researcher Award
Jingge Wang demonstrates exceptional promise and productivity as a young researcher in artificial intelligence and medical imaging. His work bridges robust machine learning and healthcare, with impactful contributions in domain generalization, generative modeling, and progression-aware disease prediction. He has published in top venues including IEEE JSTSP, Journal of the Franklin Institute, and MICCAI. Jingge excels academically, with near-perfect GPAs in both undergraduate and postgraduate studies, and has international research exposure from a collaborative visit to UT Austin. His innovative use of diffusion models and longitudinal data in medical imaging addresses pressing real-world challenges. With a record of high-impact publications, interdisciplinary work, and global collaboration, Jingge Wang stands out as an outstanding candidate for the Best Researcher Award.
🎓 Education
Jingge Wang is currently pursuing his Ph.D. in Computer Science at Tsinghua University (2022–2026), advised by Prof. Yang Li. He completed a short-term research visit to the University of Texas at Austin (2023–2024), collaborating with Prof. Qixing Huang. He holds a Master of Science in Data Science from Tsinghua University (2019–2022), graduating with an outstanding GPA of 3.98/4.0. Jingge completed his undergraduate studies in Artificial Intelligence and Automation at Huazhong University of Science and Technology (2015–2019), where he also excelled academically with a GPA of 3.97/4.0. This strong interdisciplinary foundation, combining AI, automation, and data science, positions him well to conduct impactful research at the intersection of machine learning and medical imaging.
🏢 Work Experience
Jingge Wang has diverse and impactful research experience. He is leading projects on progression-aware disease prediction and medical image generation, with a focus on exploiting temporal clinical data. He developed domain generalization models using probabilistic and Wasserstein-based methods, resulting in publications in ICLR (RobustML workshop), IEEE JSTSP, and Journal of the Franklin Institute. Jingge’s collaboration with international experts, such as Prof. Qixing Huang at UT Austin, has enriched his research vision. He has hands-on experience with latent diffusion models, generative AI, and domain-robust training techniques. His technical depth spans theoretical development and real-world applications, especially in healthcare AI. This combination of academic rigor and practical relevance exemplifies his readiness and suitability for advanced research roles.
🏅 Awards and Honors
While specific named awards are not listed, Jingge Wang’s academic and research accomplishments reflect award-worthy excellence. He graduated with top GPAs in both his B.S. (3.97/4.0) and M.S. (3.98/4.0), indicating consistent high performance. His peer-reviewed publications in competitive venues like IEEE JSTSP, MICCAI, and ISBI highlight recognition from the international academic community. He has contributed first-author work in key areas such as domain generalization and medical image synthesis, and was selected for a prestigious visiting position at the University of Texas at Austin. These achievements collectively demonstrate his scholarly distinction and strong candidacy for research excellence awards. His current work under review at MICCAI and other venues further signals continued impactful contributions.
🔬 Research Focus
Jingge Wang’s research focuses on robust machine learning, generative modeling, and medical imaging. He specializes in domain generalization, tackling the challenge of adapting models to unseen or evolving environments. His recent work integrates temporal dynamics and longitudinal data into predictive models, improving diagnostic accuracy in healthcare. He also explores controllable generative models using diffusion techniques for medical image synthesis, contributing to data augmentation and disease progression modeling. Jingge’s research bridges theory and practice—leveraging distributional robustness and probabilistic modeling for real-world generalization. Through collaboration with global researchers and publication in leading journals, he is advancing AI applications in medicine, particularly for progressive disease prediction and modality synthesis, aligning perfectly with future-facing research in AI-driven healthcare.
📊 Publication Top Notes:
-
Ji, H., Tong, H., Wang, J., Yan, D., Liao, Z., & Kong, Y. (2021). The effectiveness of travel restriction measures in alleviating the COVID-19 epidemic: evidence from Shenzhen, China. Environmental Geochemistry and Health, 1–18.
Citations: 16
-
Wang, Y.X. Jingge, Li, Y., & Xie, L. (2021). Class-conditioned Domain Generalization via Wasserstein Distributional Robust Optimization. RobustML Workshop at ICLR 2021.
Citations: 10
-
Liu, H., Wang, J., Zhang, X., Guo, Y., & Li, Y. (2024). Enhancing Continuous Domain Adaptation with Multi-path Transfer Curriculum. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 286–298.
Citations: 3
-
Xie, Y., Wang, J., Feng, T., Ma, F., & Li, Y. (2024). CCIS-Diff: A Generative Model with Stable Diffusion Prior for Controlled Colonoscopy Image Synthesis. arXiv preprint arXiv:2411.12198.
Citations: 2
-
Yang, J., Wang, J., Zhang, G., & Li, Y. (2024). Selecting the Best Sequential Transfer Path for Medical Image Segmentation with Limited Labeled Data. arXiv preprint arXiv:2410.06892.
Citations: 1
-
Wang, J., Xie, L., Xie, Y., Huang, S.L., & Li, Y. (2024). Generalizing to Unseen Domains with Wasserstein Distributional Robustness under Limited Source Knowledge. IEEE Journal of Selected Topics in Signal Processing.
Citations: 1
-
Yang, J., Zhang, G., Wang, J., & Li, Y. (2025). Adapting Foundation Models for Few-Shot Medical Image Segmentation: Actively and Sequentially. arXiv preprint arXiv:2502.01000.
Citations: Not yet cited
-
Yang, J., Zhang, G., Wang, J., & Li, Y. (2024). Graph-guided Source Selection with Sequential Transfer for Medical Image Segmentation. In: 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).
Citations: Not yet cited