📄 Download my CV

I am a PhD student in Data System Group at the Cheriton School of Computer Science at the University of Waterloo. I am so fortunate to be advised by Prof. M. Tamer Özsu. I am also a visiting researcher at ServiceNow Research. My research is on LLM applications for data management, which generally consists of two parts, 1) Structured or Semi-structured data like relational tables and knowledge graphs, and 2) Unstructured data like images and videos. I did my master degree in Data Science at City University of Hong Kong, advised by Prof. Yu Yang, working on data mining and graph learning. One thing to mention here: I am a big fan of Manchester City FC.

Education

• Ph.D in Computer Science, University of Waterloo, 2027 (expected)
• M.S. in Data Science, City University of Hong Kong, 2021
• B.Eng. in Engineering, Tongji University, 2019

News

• [Jan 2026] Two papers accepted by ICLR 2026: “GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks” and “Grounding Computer Use Agents on Human Demonstrations”. I will attend the conference in person, happy to see you there!
• [Jan 2026] I was invited to give a talk at Snowflake on “Dedicated Multi-Agent System over Heterogeneous Data Lakes”.
• [Jan 2026] I was invited by Simon Suo to give a talk at LlamaIndex on “Multimodal Learning on Documents and Beyond”.
• [Dec 2025] Paper “LazyVLM: Neuro-Symbolic Approach to Video Analytics” accepted by ICDE 2026 (Demo). I will attend the conference in person, happy to see you there!
• [Dec 2025] I gave a talk at ONDBD 2025 on “An Interactive Tool for SPARQL Query Refinement Using Natural Language Explanations”.
• [Sept 2025] Three papers accepted by NeurIPS 2025: “Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers” (Oral at MAS Workshop ICML 2025, 3k⭐ on GitHub), “The Underappreciated Power of Vision Models for Graph Structural Understanding”, and “AlignVLM: Aligning Vision-Language Models for Improved Document Understanding”.
• [May 2025] Paper “UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction” accepted by ICML 2025.
• [Jan 2025] Paper “BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks” accepted by ICLR 2025.
• [Jan 2025] Paper “Rethinking Spectral Augmentation for Contrast-based Graph Self-Supervised Learning” accepted by TMLR 2025.
• [Apr 2024] Started visiting researcher internship at ServiceNow Research in Montreal, focusing on multimodal learning and GUI understanding (Extended to May 2025).
• [Oct 2023] Two papers accepted by EMNLP 2023: “Balance Act: Mitigating Hubness in Cross-Modal Retrieval with Query and Gallery Banks” (Oral) and “InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution” (Findings).
• [Aug 2023] Paper on neural network loss landscapes accepted by IEEE BigData 2023 (Oral).
• [Jul 2023] Paper “Communication-Efficient Decentralized Online Continuous DR-Submodular Maximization” accepted by CIKM 2023.

Work experience

• Research Intern @ ServiceNow Research, 2024.04 - 2025.05.
  • Working on the vision-language model (VLM) for text-rich documents and computer use agents. Works accepted by ICLR 2025, ICML 2025, NeurIPS 2025 and ICLR 2026.
  • Mentor: I feel very fortunate to work with Sai Rajeswar and Joao Monteiro
• Research Assistant @ City University of Hong Kong & Hong Kong Institute of Data Science, 2021.10 - 2022.07.
  • Working on non-convex/submodular optimization and data mining. The Works accepted by CIKM 2023 and IEEE BigData 2023.
  • Supervisor: Prof. Yu Yang
• Teaching Assistant @ University of Waterloo, 2022.09 - now.
  • Working as a teaching assistant for courses related to database.

Publications

Please find my full set of publications on my Google Scholar page.