作者位次 #4/7ICML 2026Poster· Deep Learning / Large Language Models
ForesightKV: Optimizing KV Cache Eviction for Reasoning Models by Learning Long-Term Contribution
Zican Dong · Peiyu Liu · Junyi Li · Zhipeng Chen · Han Peng · Shuo Wang · Xin Zhao
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。
Zican Dong · Peiyu Liu · Junyi Li · Zhipeng Chen · Han Peng · Shuo Wang · Xin Zhao
Haoxiang Sun · Yingqian Min · Zhipeng Chen · Wayne Xin Zhao · Ji-Rong Wen
The rapid advancement of large reasoning models has saturated existing math benchmarks, underscoring the urgent need for more challenging evaluation frameworks. To address this, we introduce OlymMATH, a rigorously curated, Olympiad-level math benchmark comprising 350 problems, each with parallel...
Fei Bai · Yingqian Min · Beichen Zhang · Zhipeng Chen · Wayne Xin Zhao · Lei Fang · Zheng Liu · Zhongyuan Wang · Hongteng Xu