作者位次 #2/5ICML 2026Poster· Deep Learning / Large Language Models
Least-Loaded Expert Parallelism: Load Balancing An Imbalanced Mixture-of-Experts
Xuan-Phi Nguyen · Shrey Pandit · Austin Xu · Caiming Xiong · Shafiq Joty
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。
Xuan-Phi Nguyen · Shrey Pandit · Austin Xu · Caiming Xiong · Shafiq Joty
Shrey Pandit · Austin Xu · Xuan-Phi Nguyen · Yifei Ming · Caiming Xiong · Shafiq Joty
Large language model (LLM)-based reasoning systems have recently achieved gold medal-level performance in the IMO 2025 competition, writing mathematical proofs where, to receive full credit, each step must be not only correct but also sufficiently supported. To train LLM-based reasoners in such c...