作者位次 #3/5ICLR 2026Oral· Reinforcement Learning / Deep RL
Mastering Sparse CUDA Generation through Pretrained Models and Deep Reinforcement Learning
Yaoyu Wang · Hankun Dai · Zhidong Yang · Junmin Xiao · Guangming Tan
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。
Yaoyu Wang · Hankun Dai · Zhidong Yang · Junmin Xiao · Guangming Tan
Jiacheng Li · Jianchao Tan · Zhidong Yang · Pingwei Sun · FEIYE HUO · Jiayu Qin · Xiangyu Zhang · Maoxin He · Guangming Tan · Weile Jia · Xunliang Cai · Tong Zhao
Transformer architecture gradually dominates the LLM field. Recent advances in training optimization for Transformer-based large language models (LLMs) primarily focus on architectural modifications or optimizer adjustments. However, these approaches lack systematic optimization of weight pattern...