作者位次 #2/4ICLR 2026Poster· Optimization / Large Scale, Parallel and Distributed
Developmental Federated Tuning: A Cognitive-Inspired Paradigm for Efficient LLM Adaptation
Yebo Wu · Jingguang Li · Zhijiang Guo · Li Li
效率与系统OpenReview
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Yebo Wu · Jingguang Li · Zhijiang Guo · Li Li
Yebo Wu · Jingguang Li · Chunlin Tian · KaHou Tam · Zhijiang Guo · Li Li
Federated fine-tuning enables privacy-preserving LLM adaptation but faces a critical bottleneck: the disparity between LLMs’ high memory demands and edge devices’ limited capacity. To break the memory barrier, we propose Chain Federated Fine-tuning (ChainFed), an innovative paradigm that forgoes...