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

Chuan Yu

KDD 2026×2ACL 2026ICLR 2026SIGIR 2026检索与知识评测与基准推理强化学习与后训练对齐与偏好
新星分贡献者
71
一作贡献0
核心/参与41
方向广度19
合作网络9
0 一作 · 5 篇 · KDD 2026 / ACL 2026 / ICLR 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

5
作者位次 #10/12ACL 2026Findings· Findings of ACL

L o RE : Enhancing Search Relevance with Progressive Chain-of-Thought and Preference Alignment

Chenji Lu · Zhuo Chen · Hui Zhao · Zhiyuan Zeng · Gang Zhao · Junjie Ren · Lihaoran · Songyan Liu · Pengjie Wang · Chuan Yu · Yundu Huang (Taobao &amp · Zerui Huang (Taobao &amp

摘要

E-commerce search relevance is a critical component of retrieval systems. While Large Language Models (LLMs)-driven Chain-of-Thought (CoT) modeling has become the dominant paradigm and yielded significant gains, a critical gap remains: the absence of a systematic definition for comprehensive rele...

推理强化学习与后训练检索与知识OpenReview 项目页
作者位次 #9/12SIGIR 2026Oral· Information Retrieval (Full)

GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks

an Jiaotong University) · Shengyu Zhou · Jinyu Lu · Qidong Liu (Xi&#x27 · Xinhang Li · Wenlin Zhang · Feng Li · Pengjie Wang · Chuan Yu · Yundu Huang (Taobao &amp · Zerui Huang (Taobao &amp · an Jiaotong University)

摘要

Generative recommendation (GR) has shown great promise in industrial applications, particularly for candidate generation and end-to-end recommendations. However, existing GR training paradigms suffer from two fundamental mismatches with real-world deployment requirements. First, they optimize for...

对齐与偏好检索与知识多模态OpenReview

常见合作者