个人简介

林堉欣，博士，汕头大学数学与计算机学院讲师。2026年6月毕业于哈尔滨工业大学（深圳）计算机科学与技术学院，获工学博士学位，师从哈工大徐勇教授（长江学者）。2022年毕业于广东工业大学信息与工程学院，获专业硕士学位，师从凌永权(Bingo Wing-Kuen Ling)教授（青年千人）。主要研究方向为医学图像处理、计算机视觉、大模型等。

近年来，以第一作者或者通讯作者身份在本领域顶级期刊及会议IEEE Transactions on Image Processing、Pattern Recognition、AAAI、Journal of Biomedical Informatics, BIBM等重要刊物上发表学术论文十余篇。担任IEEE TCE、PR、AAAI、ACMMM、NeurIPS、ICML、CVPR等国际顶级期刊和会议审稿人。

研究方向

医学影像分析，深度学习

教育背景

2022.09~2026.06 哈尔滨工业大学（深圳） 计算机科学与技术学院

2020.09~2022.06 广东工业大学  信息与工程学院

工作经历

2026-至今，汕头大学，数学与计算机学院 讲师

代表性论文

通讯作者文章：
[1] Wong, W. K., Liu, W., Zhou, X., Hou, J., Lin, Y.^*, & Wen, J. (2026). Expert-Guided Cross-View Fusion with Self-Derived Lesion Proposals for Multi-View Diabetic Retinopathy Grading. IEEE Transactions on Image Processing. (CCF-A期刊，中科院一区，IF ：15.303)

[2] Wu, Z., Lin, Y.*, Wen, J., Shi, W., & Shen, L. (2026, March). Incomplete multi-view diabetic retinopathy grading via self-supervised inter-and intra-view restoration. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 40, No. 13, pp. 10879-10887) (CCF-A 会议).

第一作者文章：

[1] Lin, Y., Li, H., Cao, H., Hu, Y., Xu, Q., Liu, C., ... & Wang, W. (2026, March). Frequency-aligned cross-modal learning with top-K wavelet fusion and dynamic expert routing for enhanced retinal disease diagnosis. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 40, No. 9, pp. 7006-7014) (CCF-A 会议).

[2] Lin, Y., Wang, W., Luo, X., Wu, Z., Liu, C., Wen, J., & Xu, Y. (2025, April). Deep hierarchies and invariant disease-indicative feature learning for computer aided diagnosis of multiple fundus diseases. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 5, pp. 5325-5333) (CCF-A 会议).

[3] Lin, Y., Dou, X., Luo, X., Wu, Z., Liu, C., Luo, T., ... & Wang, W. (2025). Multi-view diabetic retinopathy grading via cross-view spatial alignment and adaptive vessel reinforcing. Pattern Recognition, 164, 111487 (CCF-B 期刊，中科院一区，IF：9.098).

[4] Lin, Y., Ma, J., Wang, W., Dong, S., Sun, C., Cong, W., ... & Luo, G. (2025). TransDiffECG: Semantically controllable ECG synthesis via transformer-based diffusion modeling. Journal of Biomedical Informatics, 104948(CCF-C 期刊，中科院二区，IF：5.898 ).

[5] Lin, Y., & Wang, W. (2024, December). Att-EMD-Unet: A Novel weakly supervised perspective for ECG segmentation. In 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 2170-2176). IEEE.(CCF-B 会议 ).

[6] Lin, Y., Ma, J., Wang, W., Wu, Z., Dong, S., Luo, G., & Wang, K. (2024, December). Biomedically informed ecg synthesis: Customizing cardiac cycle phases with diffusion model. In 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 3505-3508). IEEE.

ORCID ID/Scopus Author ID/Web of Science ResearcherID

ORCID ID: https://orcid.org/0000-0003-4375-3515

Google Scholar: https://scholar.google.com/citations?hl=zh-CN&user=mS3uZkwAAAAJ&view_op=list_works&sortby=pubdate