一作ICLR 2026Poster· Deep Learning / Algorithms
Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts
Shwai He · Weilin Cai · Jiayi Huang · Ang 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。
Shwai He · Weilin Cai · Jiayi Huang · Ang Li
Yibin Lei · Shwai He · Ang Li · Andrew Yates
Recent work has shown that directly fine-tuning large language models (LLMs) for dense retrieval yields strong performance, but their substantial parameter counts make them computationally inefficient. While prior studies have revealed significant layer redundancy in LLMs for generative tasks, it...