作者位次 #4/5NeurIPS 2026Poster
Accelerating Long-Context LLM Prefill via Layer-wise Progressive Token Pruning in Local Deployment
Zhongxiang Wei · Zhaohan Wang · Zhixiong Zhang · Jin Zhao · Xiaoming Fu
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。
Zhongxiang Wei · Zhaohan Wang · Zhixiong Zhang · Jin Zhao · Xiaoming Fu
Xinyu Li · Kexi Chen · Jiajie Shen · Ying Zheng · Hong Lu · Jin Zhao · Xin Wang
In multivariate long-term time series forecasting, it is widely believed that the effectiveness of self-attention arises from its attention matrix. We challenge this assumption with a counterintuitive finding: our experiments, conducted on three classic and three latest Transformer models, show t...