Xuewan He

PhD Student
University of Electronic Science and Technology of China (UESTC)
Chengdu, China

📧 hershel@std.uestc.edu.cn  ·  Google Scholar  ·  GitHub  ·  Personal Blog

Biography

I am a PhD student at the University of Electronic Science and Technology of China (UESTC). My research interests include knowledge distillation, zero-shot learning, and vision-language models.

Feel free to contact me if you are interested in discussing or collaborating.

News

• 🎉 [Feb. 2026] Co-first-author paper WaveKD: A Unified Frequency-Aware Distillation Framework for SAR Ship Recognition accepted at ICME 2026 (CCF-B).
• 🎉 [Feb. 2026] First-author paper Monotonic Rank Knowledge Distillation via Kendall Correlation accepted at IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) (CAS Q1).
• 🎉 [Jan. 2026] First-author paper PRISM: Precision-Recall Informed Data-Free Knowledge Distillation via Generative Diffusion accepted at ICASSP 2026 (CCF-B).
• 🎉 [Apr. 2024] First-author paper Cross-Domain Feature Semantic Calibration for Zero-Shot Sketch-Based Image Retrieval accepted at ICME 2024 (CCF-B).

Publications

Selected First-Author Papers

TCSVT 2026 Monotonic Rank Knowledge Distillation via Kendall Correlation
Xuewan He, J. Wang, Y. Su, D. Liu, J. Zhao, G. Lu
IEEE Transactions on Circuits and Systems for Video Technology, 2026  ·  CAS Q1

ICASSP 2026 PRISM: Precision-Recall Informed Data-Free Knowledge Distillation via Generative Diffusion
Xuewan He, J. Wang, Z. Cheng, Y. Su, S. Huang, G. Lu
IEEE International Conference on Acoustics, Speech and Signal Processing, 2026  ·  CCF-B

ICME 2024 Cross-Domain Feature Semantic Calibration for Zero-Shot Sketch-Based Image Retrieval
Xuewan He, J. Wang, Q. Xia, G. Lu, Y. Tang, H. Lu
IEEE International Conference on Multimedia and Expo, 2024  ·  CCF-B

Co-authored Papers

• ICME 2026   Cencen Liu*, Xuewan He*, Zihan Cheng, et al. WaveKD: A Unified Frequency-Aware Distillation Framework for SAR Ship Recognition  ·  CCF-B  ·  Co-first Author
• ICME 2026   Jinxin Yang, Xuewan He, Jielei Wang, et al. LatentDFKD: Resolving Ill-Posed Pixel Inversion in Data-Free Distillation through Latent Modeling  ·  CCF-B
• AAAI 2026   Shiyue Huang, Yuchen Su, …, Xuewan He, et al. Towards Distance-Invariant Radio Frequency Fingerprinting via Augmented Unsupervised Learning  ·  CCF-A
• ICASSP 2026   Zihan Cheng, Yansong Lin, Xuewan He, et al. SSCR: Efficient Multimodal Cloud Removal Framework via Exploiting Structural Semantics in SAR  ·  CCF-B
• TST 2025   Qianxin Xia, Jielei Wang, Xuewan He, et al. PEAK: Pure Logit Distillation via Multi-granularity Knowledge Transfer  ·  CAS Q2
• TCE 2024   Chengyu Ning, Guoming Lu, Xuewan He, et al. Learning Communication With Limited Range in Multi-Agent Cooperative Tasks  ·  CAS Q2

Education

• Ph.D. in Computer Science, UESTC · Institute of Intelligent Computing  ·  Sep. 2024 – Present
• M.S. in Computer Science, UESTC · School of Computer Science  ·  Sep. 2022 – Jun. 2024
• B.S. in Computer Science, UESTC · School of Computer Science  ·  Sep. 2018 – Jun. 2022