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

Yifan Gao

ACL 2026×3对齐与偏好强化学习与后训练检索与知识推理评测与基准
新星分贡献者
55
一作贡献0
核心/参与22
方向广度10
合作网络12
0 一作 · 3 篇 · ACL 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

3
作者位次 #2/10ACL 2026Findings· Findings of ACL

Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning

Fengran Mo · Yifan Gao · Sha Li · Hansi Zeng · Xin Liu · Zhaoxuan Tan · Xian Li · Jianshu Chen · Dakuo Wang · Meng Jiang

摘要

Large Language Models (LLMs) have become a popular interface for human–AI interaction, supporting information seeking and task assistance through natural, multi-turn dialogue. To respond to users within multi-turn dialogues, the context-dependent user intent evolves across interactions, requiring...

强化学习与后训练检索与知识推理OpenReview 项目页
作者位次 #9/16ACL 2026Findings· Findings of ACL

S ession I ntent B ench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E -commerce Customer Behavior Understanding

Yuqi Yang · Weiqi Wang · Baixuan Xu · Wei Fan · Qing Zong · Chunkit Chan · Zheye Deng · Xin Liu · Yifan Gao · Changlong Yu · Chen Luo · Yang Li · Zheng Li · Qingyu Yin · Bing Yin · Yangqiu Song

摘要

Session history is a common way of recording user interacting behaviors throughout a browsing activity with multiple products. For example, if an user clicks a product webpage and then leaves, it might because there are certain features that don’t satisfy the user, which serve as an important ind...

评测与基准对齐与偏好多模态OpenReview 项目页
作者位次 #10/15ACL 2026Findings· Findings of ACL

P ersona A gent: Bridging Memory and Action for Personalized LLM Agents

Weizhi Zhang · Xinyang Zhang · Chenwei Zhang · Liangwei Yang · Jingbo Shang · Zhepei Wei · Henry Peng Zou · Zijie Huang · Zhengyang Wang · Yifan Gao · Xiaoman Pan · Lian Xiong · Jingguo Liu · Philip S. Yu · Xian Li

摘要

Large Language Model (LLM) empowered agents have recently emerged as advanced paradigms that exhibit impressive capabilities in a wide range of domains and tasks. Despite their potential, current LLM agents often adopt a one-size-fits-all approach, lacking the flexibility to respond to users’ var...

对齐与偏好智能体与工具可解释性OpenReview 项目页

常见合作者