Changlun LI, Tiger

🌟 In me the tiger sniffs the rose. - Siegfried Sassoon

About Me

I am a Ph.D. student at the Data Science and Analytics Thrust, Information Hub, The Hong Kong University of Science and Technology (Guangzhou). Currently, I am a member of the DIAL, supervised by Prof. Nan Tang and co-supervised by Prof. Yuyu Luo. Also, I am the founder and CEO of Paradoox AI.

I got enrolled in The Chinese University of Hong Kong (CUHK) for my undergraduate study, and then received my B.Eng degree in Information Engineering (with minor in Computer Science) in 2020. After graduation, I worked as a Data Scientist at Measurable AI, a Silicon-Valley-Born AI startup company, for more than 3 years. I was gracefully admitted to HKUST(GZ) in Spring 2024.

Research Interests

I focus on LLM-based application research. Below are some stunning topics I am working on:

Good Data For AI: data cleaning and transformation, MegaTran.
Good AI For Fund Investment: Project Leader on DeepFund.

News

[Sep. 2025] One paper is accepted by NeurIPS 2025. See you in San Diego, USA, in Dec. 2025!
[Jul. 2025] One paper is accepted by IJCAI 2025 FinLLM Workshop. See you in Guangzhou, China, in Aug. 2025!
[Jun. 2025] Passed PhD qualifying exam. Milestone achieved!
[Apr. 2025] One paper is accepted by VLDB 2025. See you in London, United Kingdom, inSept. 2025!

Publications

NeurIPS 2025

Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking

Changlun Li, Yao Shi, Chen Wang, Qiqi Duan, Runke Ruan, Weijie Huang, Haonan Long, Lijun Huang, Yuyu Luo, Nan Tang*

Neural Information Processing Systems

PDF Code Poster Paper

VLDB 2025

Weak-to-Strong Prompts with Lightweight-to-Powerful LLMs for High-Accuracy, Low-Cost, and Explainable Data Transformation

Changlun Li, Chenyu Yang, Yuyu Luo, Ju Fan, Nan Tang*

International Conference on Very Large Data Bases

PDF Code Slide Oral with Poster

IJCAI 2025

Will LLMs be Professional at Fund Investment? DeepFund: A Live Arena Perspective

Changlun Li, Yao Shi, Yuyu Luo, Nan Tang*

International Joint Conference on Artificial Intelligence

PDF Code Slide FinLLM Workshop Oral Paper

arXiv 2025

Rise of the Community Champions: From Reviewer Crunch to Community Power

Changlun Li, Yao Shi, Yuyu Luo, Nan Tang*

PDF Project Page

arXiv 2024

SketchFill: Sketch-Guided Code Generation for Imputing Derived Missing Values

Yunfan Zhang, Changlun Li, Yuyu Luo, Nan Tang*

PDF Code

Services

Teaching Assistant

[Fall 2024] INFH5000 - Information Science and Technology: Essentials and Trends, my sharing:
[Summer 2024] HKUST(GZ) PLACE Summer Camp ☀️