Publications

Full BibTeX-backed publication list.

2026

  1. Zhao, W., Chen, Y., Ma, W., Tang, Y., Hu, S., Hu, S. X., Iacob, A., Mehrotra, A., & Lane, N. D. (2026). Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods. The Fourteenth International Conference on Learning Representations. https://openreview.net/forum?id=UFwnsmFZ6R
  2. Iacob, A., Jovanovic, A., Safaryan, M., Kurmanji, M., Sani, L., Horváth, S., Shen, W. F., Qiu, X., & Lane, N. D. (2026). MT-DAO: Multi-Timescale Distributed Adaptive Optimizers with Local Updates. The Fourteenth International Conference on Learning Representations. https://openreview.net/forum?id=5yPP238v4c
  3. Iacob, A., Sani, L., Safaryan, M., Giampouras, P., Horváth, S., Kurmanji, M., Jovanovic, A., Aleksandrov, P., Shen, W. F., Qiu, X., & Lane, N. D. (2026). DES-LOC: Desynced Low Communication Adaptive Optimizers for Foundation Models. The Fourteenth International Conference on Learning Representations. https://openreview.net/forum?id=6N2qFixxYZ

2025

  1. Guastella, A., Sani, L., Iacob, A., Mora, A., Bellavista, P., & Lane, N. D. (2025). SparsyFed: Sparse Adaptive Federated Learning. The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. https://openreview.net/forum?id=OBUQNASaWw
  2. Sani, L., Iacob, A., Cao, Z., Lee, R., Marino, B., Gao, Y., Zhao, W., Cai, D., Li, Z., Qiu, X., & Lane, N. D. (2025). Photon: Federated LLM Pre-Training. In M. Zaharia, G. Joshi, & Y. (C. Lin (Eds.), Proceedings of the Eighth Conference on Machine Learning and Systems, MLSys 2025, Santa Clara, CA, USA, May 12-15, 2025. OpenReview.net/mlsys.org. https://openreview.net/forum?id=AQgYcfg5EI
  3. Shen, W. F., Qiu, X., Kurmanji, M., Iacob, A., Sani, L., Chen, Y., Cancedda, N., & Lane, N. D. (2025). LUNAR: LLM Unlearning via Neural Activation Redirection. Advances in Neural Information Processing Systems. https://openreview.net/forum?id=teB4aqJsNP
  4. Iacob, A., Sani, L., Kurmanji, M., Shen, W. F., Qiu, X., Cai, D., Gao, Y., & Lane, N. D. (2025). DEPT: Decoupled Embeddings for Pre-training Language Models. The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. https://openreview.net/forum?id=vf5aUZT0Fz
  5. Aleksandrov, P., Kurmanji, M., Garcı́a-Redondo Fernando, O’Shea, D., Shen, W. F., Iacob, A., Sani, L., Qiu, X., Cancedda, N., & Lane, N. D. (2025). AbbIE: Autoregressive Block-Based Iterative Encoder for Efficient Sequence Modeling. CoRR, abs/2507.08567. https://doi.org/10.48550/ARXIV.2507.08567

2024

  1. Iacob, A., Sani, L., Marino, B., Aleksandrov, P., Shen, W. F., & Lane, N. D. (2024). Worldwide Federated Training of Language Models. CoRR, abs/2405.14446. https://doi.org/10.48550/ARXIV.2405.14446
  2. Sani, L., Iacob, A., Cao, Z., Marino, B., Gao, Y., Paulik, T., Zhao, W., Shen, W. F., Aleksandrov, P., Qiu, X., & Lane, N. D. (2024). The Future of Large Language Model Pre-training is Federated. CoRR, abs/2405.10853. https://doi.org/10.48550/ARXIV.2405.10853
  3. Qiu, X., Gao, Y., Sani, L., Pan, H., Zhao, W., de Gusmao, P. P. B., Alibeigi, M., Iacob, A., & Lane, N. D. (2024). FedAnchor: Enhancing Federated Semi-Supervised Learning with Label Contrastive Loss for Unlabeled Clients. CoRR, abs/2402.10191. https://doi.org/10.48550/ARXIV.2402.10191

2023

  1. Iacob, A., de Gusmão, P. P. B., Lane, N. D., Koupai, A. K., Bocus, M. J., Santos-Rodrı́guez Raúl, Piechocki, R. J., & McConville, R. (2023). Privacy in Multimodal Federated Human Activity Recognition. CoRR, abs/2305.12134. https://doi.org/10.48550/ARXIV.2305.12134
  2. Sani, L., de Gusmão, P. P. B., Iacob, A., Zhao, W., Qiu, X., Gao, Y., Fernández-Marqués, J., & Lane, N. D. (2023). High-throughput Simulation of Federated Learning via Resource-Aware Client Placement. CoRR, abs/2306.17453. https://doi.org/10.48550/ARXIV.2306.17453
  3. Iacob, A., de Gusmão, P. P. B., & Lane, N. D. (2023). Can Fair Federated Learning Reduce the need for Personalisation? In E. Yoneki & L. Nardi (Eds.), Proceedings of the 3rd Workshop on Machine Learning and Systems, EuroMLSys 2023, Rome, Italy, 8 May 2023 (pp. 131–139). ACM. https://doi.org/10.1145/3578356.3592592