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

Sungsu Lim

SIGIR 2026×2AAAI 2026ICML 2026检索与知识对齐与偏好推理评测与基准可解释性
新星分资深
19
一作贡献0
核心/参与5
方向广度16
合作网络0
0 一作 · 4 篇 · SIGIR 2026 / AAAI 2026 / ICML 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 #3/3ICML 2026Poster· Deep Learning / Graph Neural Networks

Quantile-Free Uncertainty Quantification in Graph Neural Networks

Soyoung Park · Hwanjun Song · Sungsu Lim

作者位次 #2/2SIGIR 2026Poster· Information Retrieval (Short)

StAR: Adaptive Structure-Aware Reranking for Semantic–Structural Alignment in GraphRAG

Junghyun Oh · Sungsu Lim

摘要

Retrieval-Augmented Generation (RAG) often struggles with multi-hop reasoning because Euclidean embeddings collapse hierarchical structure and let semantic similarity dominate ranking, leading to semantic–structural misalignment. As a result, structurally irrelevant yet semantically similar candi...

检索与知识推理对齐与偏好OpenReview
作者位次 #3/3SIGIR 2026Poster· Information Retrieval (Short)

DisCoRec: Disentangled Conformity-aware Recommendation with LLM-Guided Multi-View Learning

Minkyung Song · Soyoung Park · Sungsu Lim

摘要

User–item interactions in recommender systems are shaped by intertwined factors, such as genuine intent and social conformity. Recent Large Language Model (LLM)-based recommenders leverage textual semantics to improve accuracy and explainability, but often fail to disentangle these factors, limit...

检索与知识对齐与偏好评测与基准OpenReview
作者位次 #3/3AAAI 2026Poster· Artificial Intelligence

MV-LLMRec: Multi-View Representation Learning with Large Language Models for Recommendation (Student Abstract)

Minkyung Song · Soyoung Park · Sungsu Lim

可解释性OpenReview

常见合作者