👋 Yimin SHI

yiminshi📮u.🦁.edu; 施熠民

homepage_pic.jpg

Uji, Kyoto

Hi!👋 I’m Yimin, a fourth-year Computer Science Ph.D. student at the National University of Singapore (NUS=🦁), fortunate to be supervised by Prof. Xiao Xiaokui.

Previously, I received my B.Eng. in Computer Science & Engineering with honors from The Chinese University of Hong Kong, Shenzhen (LGU🐲) in 2021, graduating as the 3rd place in my major. Before starting my Ph.D. in 2023, I completed my master’s degree at NUS, where I explored AI-assisted stream processing systems with the TikTok Infra group.

My current research focuses on practical topics related to LLMs, including LLM-based personalization, conversational user profiling, information retrieval, reciprocal matchmaking, and data management.

Feel free to drop me an email if you have any questions or opportunities!

news

May 17, 2026 🎉 Our paper “GEM-Bench: A Benchmark for Ad-Injected Response Generation within Generative Engine Marketing” has been accepted by KDD 2026 Benchmark track! 🇰🇷
May 16, 2026 🎉 Our paper “NBQ: Next-Best-Question for Dynamic Profiling” has been accepted by KDD 2026 Research track! 🇰🇷
Feb 25, 2026 🎉 Our paper “Generalized Entity Matching with Adaptivity via Large Language Models” has been accepted to appear in Proceedings of the ACM on Management of Data (SIGMOD 2026)🇮🇳!
Jun 23, 2025 🎉 Our paper “ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries” has been accepted by VLDB 2025 Research track! 🇬🇧
May 16, 2025 🎉 Our paper “A Framework for Evaluating AI Agents in Open-Ended Conversations via Scripted Simulation” has been accepted by KDD 2025 Benchmark track! 🇨🇦
Apr 05, 2025 🎉 Our paper “You Are What You Bought: Generating Customer Personas for E-commerce Applications” has been accepted by SIGIR 2025 Full Papers track! 🇮🇹
Dec 24, 2024 🌞 Passed the PhD Qualification Exam, being a PhD candidate! 🍕
Aug 01, 2023 🌞 Started the PhD journey at NUS under the supervision of Prof. Xiaokui Xiao!

selected pubs

  1. NBQ_preview.png
    NBQ: Next-Best-Question for Dynamic Profiling
    Yimin Shi, Clarice Wang, Haixun Wang, and 1 more author
    In Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2026
    DOI arXiv Code Poster
  2. GEM_Bench_preview.png
    GEM-Bench: A Benchmark for Ad-Injected Response Generation within Generative Engine Marketing
    Silan Hu, Shiqi Zhang, Yimin Shi, and 1 more author
    In Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2026
    DOI arXiv Code Website
  3. generative_EM.png
    Generalized Entity Matching with Adaptivity via Large Language Models
    Xingguang Chen, Yimin Shi, and Xiaokui Xiao
    Proceedings of the ACM on Management of Data, 2026
    DOI HTML Code
  4. YAWYB_preview.png
    You Are What You Bought: Generating Customer Personas for E-commerce Applications
    Yimin Shi, Yang Fei, Shiqi Zhang, and 2 more authors
    In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2025
    arXiv Code Poster Slides
  5. script_preview.png
    A Framework for Evaluating AI Agents in Open-Ended Conversations via Scripted Simulation
    Clarice Wang*, Yimin Shi*, and Xiaokui Xiao
    In Proceedings of the 31th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2025
    HTML
  6. ThriftLLM_preview.png
    ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries
    Keke Huang, Yimin Shi, Dujian Ding, and 4 more authors
    Proceedings of the VLDB Endowment, 2025
    arXiv Code