Yulong Hui

  • huiyl22@mails.tsinghua.edu.cn
  • +86 18717351390

About Me

I am a Ph.D. student in Institute for Interdisciplinary Information Science (IIIS, Yao Class) at Tsinghua University, advised by Prof. Huanchen Zhang. Before joining Tsinghua, I obtained my B.E. of Computer Science from Shanghai Jiao Tong University in 2022. My research interests mainly lie in the fields of analytical database systems and large language models.

My current work is centered on creating effective data services powered by LLMs, through techniques like database optimization, retrieval-augmented generation and post-training.

I am actively seeking opportunities for research collaborations. Please feel free to contact me.

Research Interests

Retrieval-Augmented Generation, LLM Post-tuning, Database System

Education

Professional Experience

Alibaba Cloud

Hangzhou, China
Feb 2025 - Sept 2025

Research intern in Feitian AI Lab
Focus on: LLM Post Training for Reasoning and Agentic RL for Tool Use

Shanghai Qi Zhi Institute

Shanghai, China
June 2023 - Sept 2023

Research intern in Data System Group
Focus on Intelligent Data Analysis Framework

Tencent

Shenzhen, China
July 2021 - Sep 2021

Engineering intern in TEG, Cloud-Architecture-Platform Group
Focus on operating system and cloud infrastructure

Publications

Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrieval

Yulong Hui, Chao Chen, Zhihang Fu, Yihao Liu, Jieping Ye, Huanchen Zhang [PDF]
Under Review

Scaling LLM-based Predicates over Large Document Collections

Hengrui Zhang*, Yulong Hui*, Yihao Liu, Huanchen Zhang [PDF]
Under Review

OkraLong: A Flexible Retrieval-Augmented Framework for Long-Text Query Processing

Yulong Hui, Yihao Liu, Yao Lu, Huanchen Zhang [PDF]
Empirical Methods in Natural Language Processing (EMNLP'25, Findings)

Selective Late Materialization in Modern Analytical Databases

Yihao Liu, Shaoxuan Tang, Yulong Hui, Hangrui Zhou, Huanchen Zhang [PDF]
International Conference on Very Large Data Bases (VLDB'25)

UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysis

Yulong Hui, Yao Lu, Huanchen Zhang [PDF]
Conference on Neural Information Processing Systems (NIPS'24)

An Empirical Evaluation of Columnar Storage Formats

Xinyu Zeng, Yulong Hui, Jiahong Shen, Andrew Pavlo, Wes McKinney, Huanchen Zhang [PDF]
International Conference on Very Large Data Bases (VLDB'23)

Computing in the Era of Large Generative Models: From Cloud-Native to AI-Native

Yao Lu, Song Bian, Lequn Chen, Yongjun He, Yulong Hui, Matthew Lentz, Beibin Li, Fei Liu, Jialin Li, Qi Liu, Rui Liu, Xiaoxuan Liu, Lin Ma, Kexin Rong, Jianguo Wang, Yingjun Wu, Yongji Wu, Huanchen Zhang, Minjia Zhang, Qizhen Zhang, Tianyi Zhou, Danyang Zhuo [PDF]
Tech Report

Awards

  • Shanghai Outstanding Graduate Award
    Top 1%
  • SJTU Fan Hsu-chi Principle Scholarship
    Top 1%
  • SJTU Zhiyuan Honors Scholarship
    Top 5%
  • THU Excellent Comprehensive Scholarship
    Top 10%
  • SJTU Excellent Undergraduate Scholarship
    Top 15%
  • THU-IIIS Excellent Comprehensive Scholarship
    Top 20%

Extra Interests

  • Rock and Roll (PK Floyd, Post-Punk ...)
  • Soccer (Arsenal F.C.)
  • Singing & Guitar
  • Crosstalk
  • Stand-Up Comedy

Others

  • I am an amateur music creater certified by NetEase Cloud Music, and you can find my songs here.

    As one of the directors, with other friends, I organized the very first Tsinghua Yao Class Student Festival Gala. We also created an original theme song for it.

    For several years, I've been serving as a teaching assistant for the C++ course in Yao Class. It's always interesting to work with such brilliant freshmen.