作者位次 #2/4ICML 2026Poster· Reinforcement Learning / Deep RL
Auto-regressive In-context Demonstration Selection
Yunzhe Qi · Sirui Chen · Jiaru Zou · Jingrui He
强化学习与后训练OpenReview
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。
Yunzhe Qi · Sirui Chen · Jiaru Zou · Jingrui He
Jiaru Zou · Ling Yang · Yunzhe Qi · Sirui Chen · Mengting Ai · Ke Shen · Jingrui He · Mengdi Wang
Haobo Xu · Sirui Chen · Ruizhong Qiu · Yuchen Yan · Chen Luo · Monica Xiao Cheng · Jingrui He · Hanghang Tong
Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capabilities of Large Language Models (LLMs). However, methods such as GRPO and DAPO suffer from substantial computational cost, since they rely on sampling many rollouts for each prompt. Moreover, in R...
Jiaru Zou · Dongqi Fu · Sirui Chen · Xinrui He · Zihao Li · Yada Zhu · Jiawei Han · Jingrui He
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating them with an external knowledge base to improve the answer relevance and accuracy. In real-world scenarios, beyond pure text, a substantial amount of knowledge is stored in tables, and user questions often r...