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

Yue He

SIGIR 2026×2可解释性多模态数据与预训练对齐与偏好效率与系统
新星分新星
80
一作贡献70
核心/参与0
方向广度10
合作网络9
2 一作 · 2 篇 · 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

2
一作SIGIR 2026Oral· Information Retrieval (Full)

Same Frequency Begets Shared Interests: Popular-Niche Wavelet Graph Learning for Multimodal Recommendation

Yue He · Hongbo Chen · Jingxi Xie · Fengling Li · Jingjing Li

摘要

Multimodal recommendation systems have achieved success in capturing user interests, yet user interests are inherently diverse. Existing GCN-based methods adopt a uniform approach to model user-item interaction graphs, failing to differentiate between ''popular interests'' and ''niche interests''...

可解释性多模态数据与预训练OpenReview
一作SIGIR 2026Poster· Information Retrieval (Industry)

MedNQS: Medical State-Aware Dual-Stage Next-Turn Question Suggestion for Online Medical Consultations

Yue He · Dongsheng Bi · Minghui Yang · Jian Wang · Jinjie Gu · Junwei Liu

摘要

High-quality follow-up questions are essential for efficient online medical consultations, yet they are difficult for non-professional users to ask. Next-turn Question Suggestion (NQS) addresses this by recommending candidate questions to guide multi-turn interactions. In production, NQS faces tw...

对齐与偏好效率与系统评测与基准OpenReview

常见合作者