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

Xin Yao

ACL 2026×2FAST 2026KDD 2026检索与知识效率与系统安全评测与基准对齐与偏好
新星分贡献者
64
一作贡献0
核心/参与28
方向广度16
合作网络12
0 一作 · 4 篇 · ACL 2026 / FAST 2026 / KDD 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

4
作者位次 #6/11FAST 2026Oral· Storage & File Systems

RosenBridge: A Framework for Enabling Express I/O Paths Across the Virtualization Boundary

Shi Qiu · Li Wang · Jianqin Yan · Ruofan Xiong · Leping Yang · Xin Yao · Renhai Chen · Gong Zhang · Dongsheng Li · Jiwu Shu · Yiming Zhang

摘要

With the emergence of high-performance storage devices, the overhead of the storage stack has become a major I/O performance bottleneck. To alleviate this problem, a number of express I/O paths have been proposed based on the concept of near-data processing (NDP), such as query I/O resubmission (...

安全效率与系统评测与基准OpenReview
作者位次 #14/20ACL 2026Poster· Natural Language Processing

A uto S chema KG : Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora

Jiaxin Bai · Wei Fan · Qi Hu · Qing Zong · Chunyang Li · Hong Ting Tsang · Hongyu Luo · Yauwai Yim · Haoyu Huang · Xiao Zhou · Feng Qin · Tianshi Zheng · Xi Peng · Xin Yao · Huiwen Yang · Leijie Wu · JI Yi · Gong Zhang · Renhai Chen · Yangqiu Song

摘要

We present AutoSchemaKG, a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas. Our system leverages large language models to simultaneously extract knowledge triples and induce comprehensive schemas directly from text, modeling both entitie...

检索与知识对齐与偏好社会与人本OpenReview 项目页
作者位次 #5/7ACL 2026Findings· Findings of ACL

R ec M em: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents

Zijie Dai · Shiyuan Deng · Sheng Guan · Yizhou Tian · Xin Yao · Xiao Yan · James Cheng

摘要

Memory systems often organize user-agent interactions as retrievable external memory and are crucial for long-running agents by overcoming the limited context windows of LLMs. However, existing memory systems invoke LLMs to process every incoming interaction for memory extraction, and such an eag...

检索与知识智能体与工具可解释性OpenReview 项目页

常见合作者