作者位次 #5/5NeurIPS 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
Yi Zhao · Yajuan Peng · Cam-Tu Nguyen · Zuchao Li · Xiaoliang Wang · Xiaoming Fu · Hai Zhao
Large Reasoning Models (LRMs) achieve strong performance on complex tasks through extended chains of thought but suffer from high inference latency due to autoregressive reasoning. Recent work explores using Small Reasoning Models (SRMs) to accelerate LRM inference, yet existing frameworks such a...