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

Xiaojie Yuan

AAAI 2026ACL 2026CVPR 2026SIGIR 2026多模态社会与人本对齐与偏好推理可解释性
新星分资深
21
一作贡献0
核心/参与4
方向广度19
合作网络0
0 一作 · 4 篇 · AAAI 2026 / ACL 2026 / CVPR 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

4
作者位次 #7/7ACL 2026Poster· Natural Language Processing

Bridging the Sensory Gap: Visual Injection for Taxonomy Completion

Yuhang Niu · Hongyuan Xu · Ciyi Liu · Bofan Wei · Jiaqi Ye · Yanlong Wen · Xiaojie Yuan

摘要

Taxonomy Completion aims to automatically integrate new concepts into existing hierarchies. However, existing text-only methods suffer from a ”Sensory Gap”: they struggle to differentiate ambiguous definitions (e.g., Latte vs. Cappuccino) and miss visual grouping signals. Consequently, they often...

多模态推理可解释性OpenReview 项目页
作者位次 #8/8SIGIR 2026Oral· Information Retrieval (Full)

FairSpec: Expert Specialization for Fair LLM-based Recommendation

Yuchen Zheng · Xuan Pan · Tmall Group of Alibaba) · Chuanchang Zhang · Xi Lin · Chunyao Song · Xiangrui Cai · Xiaojie Yuan

摘要

The integration of Large Language Models (LLMs) into recommender systems has introduced a powerful paradigm for personalized recommedation. However, due to biases stemming from sensitive user attributes (e.g., gender, age), LLMs may generate discriminatory and unfair recommendations, even for use...

对齐与偏好效率与系统社会与人本OpenReview

常见合作者