| The Future of Large Language Model Pre-training is Federated L Sani, A Iacob, Z Cao, B Marino, Y Gao, T Paulik, W Zhao, WF Shen, ... Federated Foundation Models@NeurIPS 2024, 2024 | 44 | 2024 |
| Secure Vertical Federated Learning Under Unreliable Connectivity X Qiu, H Pan, W Zhao, Y Gao, PPB Gusmao, WF Shen, C Ma, ND Lane arXiv preprint arXiv:2305.16794, 2023 | 17* | 2023 |
| LLM Unlearning via Neural Activation Redirection WF Shen, X Qiu, M Kurmanji, A Iacob, L Sani, Y Chen, N Cancedda, ... NeurIPS 2025, 2025 | 15* | 2025 |
| How Data Inter-connectivity Shapes LLMs Unlearning: A Structural Unlearning Perspective X Qiu, WF Shen, Y Chen, M Kurmanji, N Cancedda, P Stenetorp, ... Evaluation and Trustworthiness of Generative AI Models @ KDD 2024, 2024 | 12* | 2024 |
| Worldwide federated training of language models A Iacob, L Sani, B Marino, P Aleksandrov, WF Shen, ND Lane Federated Foundation Models @ NeurIPS 2024, 2024 | 8 | 2024 |
| Editing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning? Z Li, X Wang, WF Shen, M Kurmanji, X Qiu, D Cai, C Wu, ND Lane AAAI 2026, 2025 | 6 | 2025 |
| Permissioned LLMs: Enforcing Access Control in Large Language Models B Jayaraman, VJ Marathe, H Mozaffari, WF Shen, K Kenthapadi NeurIPS 2025, 2025 | 5 | 2025 |
| Abbie: Autoregressive block-based iterative encoder for efficient sequence modeling P Aleksandrov, M Kurmanji, FG Redondo, D O'Shea, W Shen, A Iacob, ... arXiv preprint arXiv:2507.08567, 2025 | 3 | 2025 |
| DEPT: Decoupled Embeddings for Pre-training Language Models A Iacob, L Sani, M Kurmanji, WF Shen, X Qiu, D Cai, Y Gao, ND Lane ICLR 2025 (Oral), 2024 | 3 | 2024 |
| Compliance Cards: Automated EU AI Act Compliance Analyses amidst a Complex AI Supply Chain B Marino, Y Chaudhary, Y Pi, RJ Yew, P Aleksandrov, C Rahman, ... Regulatable ML @ NeurIPS 2024, 2024 | 3 | 2024 |
| Don't Make It Up: Preserving Ignorance Awareness in LLM Fine-Tuning WF Shen, X Qiu, N Cancedda, ND Lane arXiv preprint arXiv:2506.14387, 2025 | 2 | 2025 |
| Training AI Co-Scientists Using Rubric Rewards S Goel, R Hazra, D Jayalath, T Willi, P Jain, WF Shen, I Leontiadis, ... arXiv preprint arXiv:2512.23707, 2025 | 1 | 2025 |
| DES-LOC: Desynced Low Communication Adaptive Optimizers for Training Foundation Models A Iacob, L Sani, M Safaryan, P Giampouras, S Horváth, A Jovanovic, ... arXiv preprint arXiv:2505.22549, 2025 | 1 | 2025 |
| Balanced Accuracy: The Right Metric for Evaluating LLM Judges-Explained through Youden's J statistic S Collot, C Fraser, J Zhao, WF Shen, T Willi, I Leontiadis EACL 2026, 2025 | | 2025 |
| MT-DAO: Multi-Timescale Distributed Adaptive Optimizers with Local Updates A Iacob, A Jovanovic, M Safaryan, M Kurmanji, L Sani, S Horváth, ... arXiv preprint arXiv:2510.05361, 2025 | | 2025 |
| Towards Controlled LLM Unlearning WF Shen, X Qiu, M Kurmanji, A Iacob, L Sani, Y Chen, N Cancedda, ... Lock-LLM Workshop: Prevent Unauthorized Knowledge Use from Large Language Models, 0 | | |
Nicholas LaneUniversity of Cambridge and Flower LabsVerified email at cam.ac.uk
