William F. Shen

PhD student, University of Cambridge

Joined

January 2024

Names

William F. Shen (Preferred)

Emails

****@cam.ac.uk (Confirmed)

,

****@gmail.com

Personal Links

Career & Education History

PhD student

University of Cambridge (cam.ac.uk)

2024 – Present

Advisors, Relations & Conflicts

No relations added

Expertise

Machine Learning

Present

Federated Learning

Present

Publications

Preserving Ignorance Awareness in LLM Fine-Tuning
William F. Shen, Xinchi Qiu, Nicola Cancedda, Nicholas D. Lane
- Submitted to ICLR 2026
- Readers: Everyone
DES-LOC: Desynced Low Communication Adaptive Optimizers for Foundation Models
Alex Iacob, Lorenzo Sani, Mher Safaryan, Paris Giampouras, Samuel Horváth, Andrej Jovanovic, Meghdad Kurmanji, Preslav Aleksandrov, William F. Shen, Xinchi Qiu, Nicholas D. Lane
- ICLR 2026 Poster
- Readers: Everyone
MT-DAO: Multi-Timescale Distributed Adaptive Optimizers with Local Updates
Alex Iacob, Andrej Jovanovic, Mher Safaryan, Meghdad Kurmanji, Lorenzo Sani, Samuel Horváth, William F. Shen, Xinchi Qiu, Nicholas D. Lane
- ICLR 2026 Poster
- Readers: Everyone
Towards Controlled LLM Unlearning
William F. Shen, Xinchi Qiu, Meghdad Kurmanji, Alex Iacob, Lorenzo Sani, Yihong Chen, Nicola Cancedda, Nicholas D. Lane
- NeurIPS Lock-LLM Workshop 2025 Poster
- Readers: Everyone
Permissioned LLMs: Enforcing Access Control in Large Language Models
Bargav Jayaraman, Virendra Marathe, Hamid Mozaffari, William F. Shen, Krishnaram Kenthapadi
- NeurIPS Lock-LLM Workshop 2025 Poster
- Readers: Everyone
Editing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning?
Zexi Li, Xiangzhu Wang, William F. Shen, Meghdad Kurmanji, Xinchi Qiu, Dongqi Cai, Chao Wu, Nicholas D. Lane
- NeurIPS 2025 LLM Evaluation Workshop Poster
- Readers: Everyone
Don’t Make It Up: Preserving Ignorance Awareness in LLM Fine-Tuning
William F. Shen, Xinchi Qiu, Nicola Cancedda, Nicholas D. Lane
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Editing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning?
Zexi Li, Xiangzhu Wang, William F. Shen, Meghdad Kurmanji, Xinchi Qiu, Dongqi Cai, Chao Wu, Nicholas D. Lane
- NeurIPS Lock-LLM Workshop 2025 Poster
- Readers: Everyone
LLM Unlearning via Neural Activation Redirection
William F. Shen, Xinchi Qiu, Meghdad Kurmanji, Alex Iacob, Lorenzo Sani, Yihong Chen, Nicola Cancedda, Nicholas D. Lane
- NeurIPS 2025 poster
- Readers: Everyone
Permissioned LLMs: Enforcing Access Control in Large Language Models
Bargav Jayaraman, Virendra Marathe, Hamid Mozaffari, William F. Shen, Krishnaram Kenthapadi
- NeurIPS 2025 poster
- Readers: Everyone

View all 15 publications

Co-Authors

View all 31 co-authors