paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达
登录 DINQ
返回新星榜
RL

Rui Li

AAAI 2026×2KDD 2026×2ACL 2026ICML 2026SIGIR 2026检索与知识效率与系统强化学习与后训练数据与预训练推理
新星分贡献者
81
一作贡献30
核心/参与33
方向广度19
合作网络9
1 一作 · 7 篇 · AAAI 2026 / KDD 2026 / ACL 2026 / ICML 2026 / SIGIR 2026

获取完整研究档案

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。

联系方式

实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。

2026 顶会论文

7
一作ACL 2026Poster· Natural Language Processing

From Trajectories to Graphs: Contract-Checked Editing for Verifier-Guided LLM Reasoning

Rui Li · Shuang Cao

摘要

Inference-time search can substantially improve LLM reasoning when tasks admit deterministic verification, but existing methods largely refine single trajectories and lack a reliable mechanism for composing partial solutions across candidates. We propose contract-checked graph editing: represent...

推理可解释性效率与系统OpenReview 项目页
作者位次 #25/28SIGIR 2026Poster· Information Retrieval (Industry)

Request-Only Optimization for Recommendation Systems

Liang Guo · Wei Li · Lucy Liao · Huihui Cheng · Rui Zhang · Yu Shi · Yueming Wang · Yanzun Huang · Keke Zhai · Pengchao Wang · Timothy Shi · Xuan Cao · Shengzhi Wang · Renqin Cai · Zhaojie Gong · Omkar Vichare · Rui Jian · Leon Gao · Shiyan Deng · Xingyu Liu · Xiong Zhang · Fu Li · Wenlei Xie · Bin Wen · Rui Li · Lu Fang · Xing Liu · Jiaqi Zhai

摘要

\begin{abstract}Recommendation systems represent one of the largest machine learning applications on the planet -- industry-scale recommendation models are trained with petabytes of data and serve billions of users every day. To utilize the rich user signals in the long user history, these models...

效率与系统检索与知识长上下文与架构OpenReview
作者位次 #2/2KDD 2026Oral· Knowledge Discovery & Data Mining

From Tool Traces to Strategy Banks: Mining Failure Signatures for Budgeted Repository-Level Code Repair

Shuang Cao · Rui Li

代码检索与知识OpenReview

常见合作者