Yushu Li
Scholar

Yushu Li

Google Scholar ID: lKkYV2AAAAAJ
University of British Columbia
Natural Language ProcessingComputer VisionMachine Learning
Citations & Impact
All-time
Citations
43
 
H-index
2
 
i10-index
1
 
Publications
6
 
Co-authors
7
list available
Resume (English only)
Academic Achievements
  • 1. One paper accepted at ICCV 2025
  • 2. Two papers accepted at ICLR 2025
  • 3. 'Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selection' accepted by Transactions on Machine Learning Research (TMLR)
  • 4. 'Exploiting Vision Language Model for Training-Free 3D Point Cloud OOD Detection via Graph Score Propagation' accepted by ICLR 2025
  • 5. 'Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model' accepted by ICLR 2025
  • 6. 'On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning' accepted by ICLR 2025
  • 7. 'On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion' accepted by ICCV 2023 as Oral presentation (1.8% acceptance rate)
Research Experience
  • 1. Visiting student at the Institute for Infocomm Research (I2R), A*STAR, Singapore, working with Dr. Xun Xu and Dr. Xulei Yang
  • 2. Research intern at Shanghai Artificial Intelligence Laboratory
  • 3. Completed SIPGA program at I2R, A*STAR, Singapore
Education
  • 1. PhD Student in Electrical and Computer Engineering at the University of British Columbia (UBC), Advisor: Prof. Xiaoxiao Li
  • 2. M.Eng. in Information and Communication Engineering from South China University of Technology (SCUT), Supervisor: Prof. Kui Jia, Co-supervisor: Dr. Xun Xu
  • 3. B.Eng. from the School of Electronic and Information Engineering, SCUT
Background
  • Research interests include Natural Language Processing, Computer Vision, Reinforcement Learning, and Test-Time Adaptation. Currently a PhD student in Electrical and Computer Engineering at the University of British Columbia (UBC), a member of the Trusted and Efficient AI (TEA) Lab, advised by Prof. Xiaoxiao Li.
Miscellany
  • Personal interests not mentioned