Hi!👋 My name is Zhuowen Liang (梁卓文), I am a first-year Ph.D. student in Data Intelligence and Analytics Lab, Data Science and Analytics Thrust, The Hong Kong University of Science and Technology(Guangzhou), advised by Prof. Nan Tang. I am currently interning at Alibaba Token Foundry, working on data agent and skills. I received my bachelor degree from School of Computer Science & Engineering, South China University of Technology in 2025. I used to be a research assistant in HKUST-CIVAL group at HKUST(GZ), advised by Prof. Wei Zeng.

My current research lies on Retrieval Augmented Generation(RAG), Document Intelligence, and Information Extraction, with an emphasis on transforming large collections of unstructured documents into structured and queryable data. I am also very interested in research fields including Reinforcement Learning, LLM-Based Agent, and Data mining.

You can find my application CV here: Zhuowen Liang’s Curriculum Vitae.

🔥 News

• [Aug. 2026] 🎉 One paper was accepted to EMNLP 2026!
• [Jul. 2026] We launched the DataSpace Leaderboard. Welcome to try it!
• [May. 2026] 🎉 One paper was accepted to Transactions on Visualization and Computer Graphics (TVCG)!
• [Apr. 2026] 🎉 Our paper DataMosaic was accepted to VLDB 2026!
• [Mar. 2026] We held the KDD Cup 2026 (Data Agents for Complex Data Analysis Track).
• [Jan. 2026] 🎉 Our paper LiteCost was accepted to ICLR 2026!
• [Jul. 2025] 🎉 One paper about Cybersickness Prediction was accepted to MM 2025!
• [Apr. 2025] We proposed DataMosaic, a grounded, explainable, and verifiable framework for multi-modal data analytics with LLMs.
• [Dec. 2024] Received a PhD offer from The Hong Kong University of Science and Technology (Guangzhou).

📑 Selected Publications

(* indicates co-first authorship)

• Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs
  Zhuowen Liang, Xiaotian Lin, Zhengxuan Zhang, Yuyu Luo, Haixun Wang, Nan Tang
  ICLR 2026. Paper Code
• Beyond Tables: Doc2DB-Bench for Relationally Faithful Document-to-Database Construction
  Zhuowen Liang, Zhengxuan Zhang, Jiayang Wang, Jiazhuo Chen, Nan Tang
  arXiv 2026. Paper Code
• DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces
  Boyan Li^*, Zhuowen Liang^*, Yupeng Xie^*, Xiaotian Lin,…,Nan Tang, Guoliang Li, Yuyu Luo
  arXiv 2026. Paper Code Leaderboard
• Document-to-Database: Extraction Meets Relational Semantics
  Zhengxuan Zhang, Zhuowen Liang, Jiazhuo Chen, Haixun Wang, Nan Tang
  VLDB 2026. Paper Code
• Towards Consumer-Grade Cybersickness Prediction: Multi-Model Alignment for Real-Time Vision-Only Inference
  Yitong Zhu, Zhuowen Liang, Yiming Wu, Tangyao Li, Yuyang Wang
  ACM MM 2025. Paper

🎓 Education

• The Hong Kong University of Science and Technology(Guangzhou), Guangzhou, China
  Ph.D. student in Data Science and Analytics, 2025-Present

• South China University of Technology, Guangzhou, China
  BE in Computer Science & Technology (Elite Class), 2021-2025
  GPA: 3.93/4.0

🔎 Experience

• Alibaba (Hangzhou)
  Research Assistant @ Token Foundry, 2026.6~Present
  Research Topic: Data Agent, Agentic Skills
  

  

• The Hong Kong University of Science and Technology (Guangzhou)
  Research Intern @ Data Intelligence and Analytics Lab, 2024.10~Present
  Research Topic: Structured Reasoning combined with RAG
  Advisor: Prof. Nan Tang

  

• The Hong Kong University of Science and Technology (Guangzhou)
  Research Intern @ HKUST-CIVAL group, 2024.1~2024.9
  Research Topic: Multimodal Alignment & GraphRAG
  Advisor: Prof. Wei Zeng

  

• South China University of Technology
  Project Topic: Resident Useful Life prediction based on CNN & LSTM, 2023.11~2024.4
  Advisor: Prof. Fang Li

🏆 Honors & Awards

• Chair of the first DSA Table Talks (ICLR 2026 topic), 2026
• Tencent Enterprise First Price Scholarship, 2023 (5k RMB, Top 2% at SCUT)
• The First Price Scholarship, 2023
• The Second Price Scholarship, 2022 & 2024 (two times)
• Merit Student, 2022 & 2023 (two times)
• Excellent League Member, 2022 & 2023 & 2024 (three times)
• Chinese Mathematics Competitions(Guangdong): First Prize, 2022
• Asia and Pacific Mathematical Contest in Modeling(APMCM): Third Prize, 2023
• MathorCup College Mathematical Modeling Challenge: Third Prize, 2023
• China Undergraduate Mathematical Contest in Modelling(Guangdong): Third Prize, 2022

🚶 Services

• Committee Chair of KDD Cup 2026 (Data Agents for Complex Data Analysis Track)
• Conference Reviewer: NeurIPS 2026, ICLR 2027