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

Huan Huo

ICML 2026×3KDD 2026SIGIR 2026效率与系统检索与知识对齐与偏好长上下文与架构数据与预训练
新星分资深
37
一作贡献0
核心/参与30
方向广度16
合作网络6
0 一作 · 5 篇 · ICML 2026 / KDD 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

5
作者位次 #2/4ICML 2026Poster· General Machine Learning / Sequential, Network, and Time Series Modeling

CARE: Adaptive Calibration for Reliable Recommendations

Nitin Bisht · Huan Huo · Xiuwen Gong · Guandong Xu

作者位次 #4/4ICML 2026Poster· General Machine Learning / Scalable Algorithms

FedEMoE: Improving Personalization on Heterogeneous Federated Learning via Elastic Mixture of Experts Architecture

Haizhou Du · Lixin Huang · Zonghan Wu · Huan Huo

对齐与偏好效率与系统长上下文与架构OpenReview
作者位次 #4/6SIGIR 2026Oral· Information Retrieval (Full)

Diagnosing and Mitigating Mid-Sequence Degradation in Recommender Systems

Linjiang Guo · Nitin Bisht · Shiqing Wu · Huan Huo · Xianzhi Wang · Guandong Xu

摘要

Although attention-based sequential recommenders have achieved strong accuracy, they can exhibit a systematic failure mode, i.e., lost-in-the-middle, where attention disproportionately concentrates on sequence boundaries to informative middle behaviors. Through controlled perturbations, we find t...

检索与知识效率与系统数据与预训练OpenReview

常见合作者