作者位次 #4/7ICLR 2026Poster· Deep Learning / Everything Else
MLP Memory: A Retriever-Pretrained Memory for Large Language Models
Rubin Wei · Jiaqi Cao · Jiarui Wang · Jushi Kai · Qipeng Guo · Bowen Zhou · Zhouhan Lin
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。
Rubin Wei · Jiaqi Cao · Jiarui Wang · Jushi Kai · Qipeng Guo · Bowen Zhou · Zhouhan Lin
Jushi Kai · Yixuan Wang · Boyi Zeng · Haoli Bai · Bo Jiang · Ziwei He · Zhouhan Lin
Hongru WANG · Rui Wang · Jushi Kai · Boyang XUE · Yongqi Li · Shijue Huang · Xiaoteng Ma · Jeff Z. Pan · Amos Storkey
Long-horizon agents operate over extended sequences of reasoning and actions, but this inevitably accumulates context noise, resulting in excessive computational cost and information overload. Existing approaches commonly rely on fixed, rule-based summarization strategies (e.g., summarizing every...