作者位次 #6/7ICLR 2026Poster· Deep Learning / Algorithms
Toward Principled Flexible Scaling for Self-Gated Neural Activation
Sudong Cai · Shuyuan Zheng · Bingzhi Chen · Shuai Yuan · Chuan Xiao · Jianbin Qin · Bing WANG
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。
Sudong Cai · Shuyuan Zheng · Bingzhi Chen · Shuai Yuan · Chuan Xiao · Jianbin Qin · Bing WANG
Ziyang Wang · Jiangfeng Xiao · Chuan Xiao · Ruoxiang Li · Rui Mao · Jianbin Qin
Large language models (LLMs) are expensive to serve because dense FFN blocks, multi-head attention, and KV caches dominate memory, making structured pruning a natural way to reduce serving costs under tight parameter and memory budgets. We present GRASPrune, a global budgeted structured pruning f...