作者位次 #2/4ICML 2026Poster· Deep Learning / Large Language Models
Many-Shot CoT-ICL: Making In-Context Learning Truly Learn
Tsz Ting Chung · Lemao Liu · Mo Yu · Dit-Yan Yeung
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。
Tsz Ting Chung · Lemao Liu · Mo Yu · Dit-Yan Yeung
Junjie Wu · Jiangnan Li · Yuqing Li · Lemao Liu · Liyan Xu · Jiwei Li · Dit-Yan Yeung · Jie Zhou · Mo Yu
Retrieval-augmented generation (RAG) over long documents typically involves splitting the text into smaller chunks, which serve as the basic units for retrieval. However, due to dependencies across the original document, contextual information is often essential for accurately interpreting each c...
Xuanfan Ni · Liyan Xu · Chenyang Lyu · Longyue Wang · Mo Yu · Lemao Liu · Fandong Meng · Jie Zhou · Piji Li
To reduce memory consumption during LLM inference, a handful of methods have been proposed for KV cache pruning.While these techniques can accomplish lossless memory reduction on many datasets, they often hinge on an under-emphasized condition: an input/domain-specific threshold for KV cache budg...
Jingxuan Liu · Zhi Qu · Jin Tei · Hidetaka Kamigaito · Lemao Liu · Taro Watanabe
Automatic evaluation metrics are essential for building multilingual translation systems. The common practice of evaluating these systems is averaging metric scores across languages, yet this is suspicious since metrics may suffer from cross-lingual scoring bias, where translations of equal quali...