Xinyu Yan

PhD student, College of Computing and Data Science, Nanyang Technological University

MS student, College of Computing and Data Science, Nanyang Technological University

Joined

November 2024

Names

Xinyu Yan (Preferred)

Yan Xinyu

Emails

****@outlook.com (Confirmed)

****@e.ntu.edu.sg (Confirmed)

Personal Links

Google Scholar

DBLP

ORCID

Career & Education History

PhD student

College of Computing and Data Science, Nanyang Technological University (ntu.edu.sg)

2026 – Present

MS student

College of Computing and Data Science, Nanyang Technological University (ntu.edu.sg)

2024 – 2026

Undergrad student

School of Computer Engineering and Science, Shanghai University (shu.edu.cn)

2020 – 2024

Advisors, Relations & Conflicts

PhD Advisor

Wei Yang Bryan Lim

2024 – Present

Expertise

Trustworthy AI

2026 – Present

Machine Unlearning

2025 – Present

Machine Learning System

2024 – Present

Artificial Intelligence

2023 – Present

Publications

MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models
Tiantong Wang, Yan Xinyu, Tiantong Wu, Yurong Hao, Yong Jiang, Fei Huang, Wei Yang Bryan Lim
- CoRR 2026
- Readers: Everyone
Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language Models
Fuyao Zhang, Yan Xinyu, Tiantong Wu, Wenjie Li, Tianxiang Chen, Yang Cao, Ran Yan, Longtao Huang, Wei Yang Bryan Lim, Qiang Yang
- AAAI 2026
- Readers: Everyone
Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language Models
Fuyao Zhang, Xinyu Yan, Tiantong Wu, Wenjie Li, Tianxiang Chen, Yang Cao, Ran Yan, Longtao Huang, Wei Yang Bryan Lim, Qiang Yang
- The Fortieth AAAI Conference on Artificial Intelligence (AAAI 2026) Poster
- Readers: Everyone
AdaCache: Adaptive Caching and Context Augmentation for Efficient LLM Serving
Zeng Zihao, Siyi Li, Xinyu Yan, Lei Xiao, Wei Yang Bryan Lim
- ICLR 2026 Poster
- Readers: Everyone
Verifiably Forgotten? Gradient Differences Still Enable Data Reconstruction in Federated Unlearning
Fuyao Zhang, Wenjie Li, Yurong Hao, Xinyu Yan, Ran Yan, Yang Cao, Wei Yang Bryan Lim
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
FedRAM: Federated Reweighting and Aggregation for Multi-Task Learning
Fan Wu, Xinyu Yan, Jiabei Liu, Wei Yang Bryan Lim
- NeurIPS 2025 poster
- Readers: Everyone
Verifiably Forgotten? Gradient Differences Still Enable Data Reconstruction in Federated Unlearning
Fuyao Zhang, Wenjie Li, Yurong Hao, Xinyu Yan, Yang Cao, Wei Yang Bryan Lim
- CoRR 2025
- Readers: Everyone

Xinyu Yan

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models

Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language Models

Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language Models

AdaCache: Adaptive Caching and Context Augmentation for Efficient LLM Serving

Verifiably Forgotten? Gradient Differences Still Enable Data Reconstruction in Federated Unlearning

FedRAM: Federated Reweighting and Aggregation for Multi-Task Learning

Verifiably Forgotten? Gradient Differences Still Enable Data Reconstruction in Federated Unlearning

Co-Authors