Scholar
Li Ju
Google Scholar ID: tlXTHUEAAAAJ
Department of Information Technology, Uppsala University
Citations & Impact
Citations
193
H-index
5
i10-index
4
Publications
9
Co-authors
6
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Paper 'Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere' accepted by NeurIPS 2025.
- Team Cat Quartet won 2nd place (1st in Europe) at Huawei Wireless Communication Global Hackathon 2025.
- Team Hello Kitty secured 2nd place at Huawei Sweden Hackathon 2024.
- Poster presentation at Swedish e-Science Academy about logit adjustment in heterogeneous federated learning.
- Paper 'Accelerating Fair Federated Learning: Adaptive Federated Adam' accepted by IEEE Transactions on Machine Learning in Communications and Networking.
- Paper 'Federated Learning for Predicting Compound Mechanism of Action Based on Image-data from Cell Painting' accepted by Artificial Intelligence in the Life Sciences.
- Paper 'Blades: A Unified Benchmark Suite for Byzantine Attacks and Defenses in Federated Learning' accepted by IoTDI ‘24.
- Poster presentation at Swedish e-Science Academy about accelerating fair federated learning in Umeå, Sweden.
- Released Blades, a simulator for Byzantine-robust federated learning with attacks and defenses.
- Paper 'Proactive autoscaling for edge computing systems with kubernetes' accepted by UCC ‘21.
Research Experience
- During Ph.D. studies at Uppsala University, participated in multiple research projects including developing a denoising neural SVD operator for wireless communications, using machine learning methods to solve wireless localization problems, etc.
Education
- Ph.D. candidate in Scientific Computing at Uppsala University, supervised by Associate Professor Andreas Hellander; M.Sc. in Computational Science, Uppsala University; M.Sc. in Chemometrics, University of Science and Technology of China; B.Sc. in Chemistry, University of Science and Technology of China.
Background
- Research Interests: Learning from distributed heterogeneous data, particularly interested in data heterogeneity problems in federated learning and uncertainty quantification for multi-modal language models.
Miscellany
- Personal interests not mentioned.
