Xinyao Li

Email | CV | Google Scholar

• I am currently exploring opportunities in academia and industry. Please feel free to reach out.

I am a fourth-year Ph.D student in Successive Postgraduate and Doctoral Program at School of Computer Science and Engineering, University of Electronic and Science and Technology of China (UESTC), supervised by Prof. Jingjing Li. I was a visiting PhD student at CFAR, A*STAR from August 2025 to August 2026, co-supervised by Prof. Ivor Tsang and Dr. Hangwei Qian. Before that, I earned my bachelor’s degree in Computer Science and Technology from UESTC in 2022.

I focus on efficient knowledge transfer and generalization of pretrained models, including domain adaptation, domain generalization, and related transfer settings, with applications to computer vision, multimodal models, and beyond. I am also interested in AI for Science in fields including Composite Materials Design, Remaining Useful Life (RUL) prediction, State of Charge (SOC) prediction of batteries, etc.

Publications

Journal Papers

• Learning Ordinality-Aware Multimodal Representations for Composite Materials Design [Paper] [Code]
  Xinyao Li, Hangwei Qian, Jingjing Li, Lei Zhu, Ivor Tsang.
  Nature Communications, 2026.
• Unified Modality Separation: A Vision‑Language Framework for Unsupervised Domain Adaptation [Paper] [Code]
  Xinyao Li, Jingjing Li, Zhekai Du, Kei Zhu, Heng Tao Shen.
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025.
• Efficient Transfer Learning of Large Models with Limited Resources: A Survey [Paper]
  Xinyao Li, Jingjing Li, Lei Zhu, Heng Tao Shen.
  Chinese Journal of Computers，2024.
  （李鑫尧, 李晶晶, 朱磊, 申恒涛, “资源受限的大模型高效迁移学习算法研究综述,” 计算机学报, 2024.）
• Generalizing Vision-Language Models to Novel Domains: A Comprehensive Survey [Paper]
  Xinyao Li, Jingjing Li, Fengling Li, Lei Zhu, Yang Yang, Heng Tao Shen.
  ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), 2026.
• Domain Adaptive Remaining Useful Life Prediction with Transformer [Paper] [Code]
  Xinyao Li, Jingjing Li, Lin Zuo, Lei Zhu, Heng Tao Shen.
  IEEE Transactions on Instrumentation and Measurement (TIM), 2022.
• Cross-Domain State Estimation of Lithium-ion Batteries: A Review [Paper]
  Xinyao Li, Hongbo Chen, Liyuan Shen, Xuesong Feng, Jingjing Li.
  Journal of University of Electronic Science and Technology of China, 2024.
  （李鑫尧, 陈洪波, 沈力源, 冯雪松, 李晶晶, “锂电池状态跨域估计算法综述,” 电子科技大学学报, 2024.）

Conference Papers

• Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation [Paper] [Code]
  Xinyao Li, Zhekai Du, Fengling Li, Ke Lu, Jingjing Li.
  in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
• Generalizing Vision-Language Models with Dedicated Prompt Guidance [Paper] [Code]
  Xinyao Li, Yinjie Min, Hongbo Chen, Zhekai Du, Fengling Li, Jingjing Li.
  in Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2026.
• Agile Multi-Source-Free Domain Adaptation [Paper] [Code]
  Xinyao Li, Jingjing Li, Fengling Li, Lei Zhu, Ke Lu.
  in Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2024.
• PatAug: Augmentation of Augmentation for Test‑Time Adaptation [Paper] [Code]
  Xinyao Li, Dan Zhang, Zhekai Du, Lei Zhu, Zhi Chen, Jingjing Li.
  in Proceedings of the 33rd ACM International Conference on Multimedia (ACM MM), 2025.
• Source-Free Active Domain Adaptation via Energy-Based Locality Preserving Transfer [Paper] [Code]
  Xinyao Li, Zhekei Du, Jingjing Li, Lei Zhu, Ke Lu.
  in Proceedings of the 30th ACM International Conference on Multimedia (ACM MM), 2022.
• CONGA: Confidence-and-Gradient-Aware Learning Rate Schedule for Test-Time Adaptation [Paper]
  Shaoran Lv*, Xinyao Li*, Jingjing Li.
  in Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026.
• Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation [Paper] [Code]
  Zhekai Du, Xinyao Li, Fengling Li, Ke Lu, Lei Zhu, Jingjing Li.
  in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

Awards

• Doctoral National Scholarship, 2025
• Doctoral National Scholarship, 2024
• UESTC Academic Scholarship, First Prize, 2025
• UESTC Academic Scholarship, First Prize, 2024