4 citations · 5 across the 11 of their papers we have counts for
Showing 2026 · cs.LGShow all
2 papers · 2 filters
cs.LG2026
Byzantine-Resilient Federated Large Language Model via Hypergraph Message Passing
Kai Li, Hanlin Cai, Zihao Liu +5
Federated Large Language Models (FedLLMs) are promising to deliver privacy-preserving, collaborative intelligence. The decentralized training process is vulnerable to Byzantine att…
cs.LG2026
FedLNS: Leverage LayerNorm Signature Modeling to Mitigate Adversarial Manipulation in Federated LLMs
Kai Li, Jong-Ik Park, Carlee Joe-Wong +2
Federated training enables language models to learn from distributed private text, but the server cannot directly verify the local supervision or optimization process that produces…