Hi, I’m Xinrui He.

I am a fourth-year Ph.D. candidate in Computer Science at the University of Illinois Urbana-Champaign, advised by Prof. Jingrui He. My research develops applied machine learning methods for personalization and reliable decision support, with a focus on recommender systems, graph learning, healthcare ML, and LLM post-training.

Prior to UIUC, I received my M.S. and B.S. degrees in Computer Science and Technology from Xi’an Jiaotong University, advised by Prof. Xiaoshe Dong. I also received a dual degree in General Engineering from Ecole Centrale de Lille.

During my studies, I have been fortunate to receive several honors, such as the ICLR 2026 Workshop Outstanding Paper Award, the NSF Student Travel Award, the Conference Presentation Award at UIUC, and the Outstanding Graduate and First-Class Scholarship at XJTU.

News

  • 2026.05 I began my internship at Amazon.
  • 2026.05 Our paper "SafeImpute: Reliable Clinical Data Imputation via Conformal Selection" was accepted to KDD 2026.
  • 2026.04 Our paper "RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking" received an Outstanding Paper Award at the ICLR 2026 Workshop.
  • 2026.01 Our paper "FeDecider: An LLM-Based Framework for Federated Cross-Domain Recommendation" was accepted to WWW 2026.
  • 2025.05 Our paper "LLM-Forest: Graph-augmented In-context Ensemble Learning of LLMs for Data Imputation" was accepted to Findings of ACL 2025.

Publications

(* equal contribution)

Selected Papers

SafeImpute paper overview figure
SafeImpute: Reliable Clinical Data Imputation
via Conformal Selection
Xinrui He, Mengting Ai, Junting Wang, Curtiss Cook, Jingrui He.

Reliable clinical data imputation with event graphs and conformal selection.

KDD 2026

FeDecider paper overview figure
FeDecider: An LLM-Based Framework for Federated Cross-Domain Recommendation
Xinrui He, Ting-Wei Li, Tianxin Wei, Xuying Ning, Xinyu He, Wenxuan Bao, Hanghang Tong, Jingrui He.

Federated LLM recommendation with directional LoRA sharing and data-aware integration under domain heterogeneity.

WWW 2026 [paper][code]

LLM-Forest paper overview figure
LLM-Forest: Graph-augmented In-context Ensemble Learning of LLMs for Data Imputation
Xinrui He, Yikun Ban, Jiaru Zou, Tianxin Wei, Curtiss B. Cook, Jingrui He.

Graph-augmented LLM ensembles for robust tabular data imputation.

Findings of ACL 2025 [paper][code]

CoFedRec paper overview figure
CoFedRec: Co-clustering for Federated Recommender System
Xinrui He, Shuo Liu, Jackey Keung, Jingrui He.

Co-clustering users and items to improve federated recommendation.

WWW 2024 [paper][code]

BNCL paper overview figure
BNCL: Robust Basket Recommendation via Noise-tolerated Graph Contrastive Learning
Xinrui He*, Tianxin Wei*, Jingrui He.

Noise-tolerant graph contrastive learning for basket recommendation.

CIKM 2023 [paper][code]

Other Publications

  • ACL 2026 ICLR 2026 Workshop RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking
    Jiaru Zou, Dongqi Fu, Sirui Chen, Xinrui He, Zihao Li, Yada Zhu, Jiawei Han, Jingrui He. Outstanding Paper. [paper][code]
  • Future Science OA HbA1c Trend Prediction for Diabetes Mellitus with GANs and LLMs
    Yikun Ban, Xinrui He, Patricia Verona, Curtiss Cook, Jingrui He. [paper]
  • KDD 2025 Connecting Domains and Contrasting Samples: A Ladder for Domain Generalization
    Tianxin Wei*, Yifan Chen*, Xinrui He, Wenxuan Bao, Jingrui He. [paper][code]
  • CIKM 2025 PyG-SSL: A Graph Self-supervised Learning Toolkit
    Lecheng Zheng, Baoyu Jing, Zihao Li, Zhichen Zeng, Tianxin Wei, Mengting Ai, Xinrui He, Lihui Liu, Dongqi Fu, Jiaxuan You, Hanghang Tong, Jingrui He. [paper][code]
  • HPCC 2021 DMF-MPC: A Dual-Stage and Multi-Step Forecasting Model Based Cooling System Control Method for Data Center Energy Cost Minimization
    Xinrui He, Weiduo Chen, Xiaoshe Dong, Qiang Wang, Jialin Liu, Fan Dong, Yuanqi Su. [paper]

Experience

Amazon
May 2025 - Aug 2025
Applied Scientist Intern. Built an LLM-enhanced universal user representation framework for personalization and recommendation.
Tencent
May 2021 - Jul 2021
Machine Learning Intern. Proposed and deployed a CVR prediction model for online video recommendation.
Goaland / École Centrale de Lille
Feb 2018 - Jan 2019
R&D Project on product information management. Designed an algorithm to refine product descriptions using multimodal product information.
CRIStAL, Lille
Jan 2018 - Feb 2018
Software Development Engineering Intern with Prof. Ahmed Rahmani. Developed computer vision software for educational purposes.