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

Junlin Zhu

SIGIR 2026×2可解释性对齐与偏好数据与预训练检索与知识推理
新星分新星
69
一作贡献40
核心/参与9
方向广度10
合作网络6
1 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
作者位次 #4/6SIGIR 2026Oral· Information Retrieval (Full)

Balanced Frequency Decoupling: Energy-Aware Multi-Scale Preference Modeling for Sequential Recommendation

Jiahao Hu · Wei Zhou · Jie Liao · Junlin Zhu · Junhao Wen · Hongyu Zhang

摘要

Frequency-domain sequential recommendation models enhance sequence representation capacity through spectral transformations. However, existing methods typically adopt coarse-grained spectrum reweighting strategies that strengthen high-frequency components while amplifying random noise within freq...

对齐与偏好可解释性数据与预训练OpenReview
一作SIGIR 2026Oral· Information Retrieval (Full)

Towards Conflict-aware Selective Knowledge Unlearning for Continual Few-shot Knowledge Graph Completion

Junlin Zhu · Bo Fu · Guiduo Duan

摘要

Few-shot knowledge graph completion (FKGC) aims to enhance knowledge reasoning for newly emerging relations using only a limited number of supporting triples. Given the inherent growth and evolution of knowledge graphs (KGs), FKGC faces greater challenges in continual learning (CL) scenarios, as...

检索与知识可解释性推理OpenReview

常见合作者