作者位次 #2/5ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders
LouisKV: Efficient KV Cache Retrieval for Long Input-Output Sequences
WENBO WU · Qingyi Si · Xiurui Pan · Ye Wang · Jie Zhang
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。
WENBO WU · Qingyi Si · Xiurui Pan · Ye Wang · Jie Zhang
Chenxu Yang · Qingyi Si · Yongjie Duan · Zheliang Zhu · Chenyu Zhu · Qiaowei Li · Minghui Chen · Zheng Lin · Weipinng Wang
Ziheng Li · Liu Kang · Feng Xiao · Luxi Xing · Qingyi Si · Zhuoran Li · Weikang Gong · Deqing Yang · Yanghua Xiao · Hongcheng Guo
Group Relative Policy Optimization (GRPO) has emerged as a promising critic-free reinforcement learning paradigm for reasoning tasks. However, standard GRPO employs a coarse-grained credit assignment mechanism that propagates group-level rewards uniformly to to every token in a sequence, neglecti...
Ziyi Cao · Qingyi Si · Jingbin Zhang · Bingquan Liu
Chenxu Yang · Qingyi Si · Mz Dai · Dingyu Yao · Mingyu Zheng · Minghui Chen · Zheng Lin · Weiping Wang
Chenxu Yang · Qingyi Si · Lanrui Wang · Zheng Lin