作者位次 #2/7ICML 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
Yihan Wang · Peiyu Liu · Runyu Chen · Wei Xu
Gen Li · Peiyu Liu
Vision–Language Models (VLMs) excel at visual reasoning but still struggle with external knowledge integration. Retrieval-Augmented Generation(RAG) is a promising solution, but current methods remain inefficient and often fail to maintain high answer quality. To address these challenges, we propo...
Yihan Wang · Peiyu Liu · Runyu Chen · Jiaxing Pu · Wei Xu
Text-to-SQL technology has evolved rapidly, with diverse academic methods achieving impressive results. However, deploying these techniques in real-world systems remains challenging due to limited integration tools. Despite these advances, we introduce Squrve, a unified, modular, and extensive Te...
Yongxuan Wu · Runyu Chen · Peiyu Liu · Hongjin Qian
Long-context understanding poses significant challenges in natural language processing, particularly for real-world dialogues characterized by high redundancy and uneven information density. Although large language models (LLMs) achieve impressive results on existing benchmarks, these datasets fa...