avatar

Wenxin Su

Ph.D. Candidate📍EMBL, Heidelberg, Germany

🧬 About Me

Hi, I am Wenxin Su, a Ph.D. candidate at the European Molecular Biology Laboratory (EMBL), Heidelberg, supervised by Dr. Anna Kreshuk.

Before starting my Ph.D., I completed my master at University of Shanghai for Science and Technology in 2025. During this time, I conducted research in Source-free Domain Adaptation and Prompt Learning under the guidance of Dr. Song Tang.

I am interested in developing transfer learning, representation learning, and multimodal learning methods for biological image analysis.

💬 I’m always open to collaboration and discussion — if you’re interested in my research or have exciting ideas, feel free to reach out to me 😊!


📰 News

  • Sep, 2025 — Joined the European Molecular Biology Laboratory (EMBL), Heidelberg for a Ph.D.! 🎓
  • Jun, 2025 — Graduated from University of Shanghai for Science and Technology! 🎓
  • Feb, 2025 — Our paper, “Domain Adaptive Diabetic Retinopathy Grading with Model Absence and Flowing Data”, has been accepted by CVPR 2025 !
  • Jan, 2025 — Our paper, “Proxy Denoising for Source-Free Domain Adaptation”, has been accepted by ICLR 2025! Oral TOP1.8% 🏆
  • Dec, 2024 — Our paper, “Is Foreground Prototype Sufficient? Few-Shot Medical Image Segmentation with Background-Fused Prototype” is out!
  • Mar, 2024 — Our paper, “Unified source-free domain adaptation” is out!
  • Feb, 2024 — Our paper, “Source-free domain adaptation with frozen multimodal foundation model” has been accepted by CVPR 2024!
  • Jun, 2024 — Our paper, “Model adaptation via credible local context representation”, has been accepted by CAAI Transactions on Intelligence Technology !

📚 Publications


CVPR
CVPR Paper

Domain Adaptive Diabetic Retinopathy Grading with Model Absence and Flowing Data

Wenxin Su, Song Tang, Xiaofeng Liu, Xiaojing Yi, Mao Ye, Chunxiao Zu, Jiahao Li, and Xiatian Zhu
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025


ICLR Oral
CVPR Paper

Proxy Denoising for Source-Free Domain Adaptation

Song Tang, Wenxin Su, Mao Ye, and Xiatian Zhu
International Conference on Learning Representations (ICLR) 2025 (Oral, TOP1.8%), 2025


CVPR
CVPR Paper

Source-Free Domain Adaptation with Frozen Multimodal Foundation Model

Song Tang, Wenxin Su, Mao Ye, and Xiatian Zhu
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024


Arxiv
CVPR Paper

Unified Source-free Domain Adaptation

Song Tang, Wenxin Su, Mao Ye, Jianwei Zhang, and Xiatian Zhu