Jinyang Li

JINYANG LI

Hi, I'm Jinyang Li who is a final-year Ph.D. student in Computer Science at the University of Hong Kong, advised by Prof. Reynold Cheng specializing in data-centric code generation, large language model agents, and interactive data intelligence. I found BIRD-SQL, a widely-used benchmark ecosystem adopted by leading companies and research institutes. My research has been published in top-tier venues including NeurIPS, ICLR, ICML, ACL, AAAI, KDD, and EMNLP. During PhD, I'm honored to collaborate with major research labs through internships and projects at Microsoft Research, Alibaba DAMO, Amazon Alexa, and Google Cloud GenAI, focusing on resolving real-world problems and exploring new computing use via agentic coding. My research is supported by the HKU Presidential PhD Fellowship. My research goal is to architect reliable, user-centric LLM agentic systems that redefine the efficiency of real-world analysis and science.

EDUCATION

Ph.D. Department of Computer Science, Hong Kong University, HK Ph.D in Department of Computer Science Research interests: LLM, Data Analysis Agents, Text-to-SQL Advisor: Prof. Reynold CK Cheng Date: Jan. 2022 - Now.
M.S. School of Fu Foundation of Engineering & Applied Science, Columbia University, U.S. M.S. in Department of Electrical Engineering Track: Data-Driven Analysis and Computing, Data Science Institute Research interests: Natural Language Processing, Computer Vision in Health Care Date: Aug. 2018 - Feb. 2020.
B.E. School of Electrical Engineering and Automation, Harbin Institute of Tech, China B.E. in Department of Electrical Engineering Research Intern: The University of Nottingham, advised by Prof. Chris Gerada Advisor: Prof. Shiyan Yang & Prof.Ping Zheng Date: Aug. 2013 - June. 2017.

RECENT NEWS

06-02-2026 ------------ Our BIRD-Interact has been accepted to ICLR 2026 as an Oral (1-1.5%)! See you in Rio!

18-09-2025 ------------ 2 papers have been accepted to NeurIPS Main! Sincerely thank Jack Willams and the MSR Calc Intel team for great supervision and chilled summer in Cambridge. I feel grateful for insightful collaborations with Google Cloud experts. And of course, thanks for my professor and folks in BIRD Team, you made me! 🎉🎉🎉~

15-05-2025 ------------ 2 papers have been accepted to ACL Main, and 1 paper has been accepted to KDD. 🎉🎉🎉~

01-05-2025 ------------ 1 paper has been accepted to ICML 2025. 🎉

21-09-2023 ------------ Our paper has been accepted to NeurIPS 2023 as a Spotlight! Additionally, we released a cleaner version of dev set, please download it again at Bird-SQL benchmark.

ACADEMIC EXPERIENCES

Amazon, Cambridge, UK Applied Scientist Intern Alignment & RL for Conversational Modeling Date: Sept. 2025 - March. 2026
Microsoft Research, Cambridge, UK Researcher Summer Intern Project I: Non-Parametric Knowledge Distillation For Data Science Code Generation Date: May. 2024 - Sept. 2024 Project II: Code Generation w/ RL for New Computing Use Date: Jun. 2025 - Sept. 2025
ConvAI, Alibaba DAMO Academy, Beijing, China Advisor: Binyuan Hui & Yongbin Li & Fei Huang & Prof.Reynold C.K. Cheng Project I: Graphix-T5: Enhancing T5's Database Schema Comprehension through Efficient Multi-Hop Reasoning Project II: BIRD: The Most Comprehensive Cross-domain Text-to-SQL benchmark for Realistic Database Contents Grounding Date: Jun. 2022 - Mar. 2023
IBM Massachusetts Institute of Technology Waston (MIT-IBM), Boston, U.S. Advisor: Researcher Fan Zhang Project: The Research, Design, and Implement of AI Dialog System Based on Goal Planning and Deep Learning Date: Aug. 2019 - Jan. 2020
State Key Laboratory of Intelligent Technology and Systems, TSAIL Group, Tsinghua University, Beijing, China Advisor: Prof. Jun Zhu Project: Shapelet Based Time Series Regularized Decision Tree & Adversarial Attack for ML models Date: Apr. 2019 - Aug. 2019
Google Ai & Data Science Institute, DSI, Columbia University, New York, U.S. Advisor: Researcher Joshua Gordon & Prof. Kathy McKeown Project: Cancer Metastases on Gigapixel Pathology Images in Low Devices Date: Jan. 2019 - April. 2019

PUBLICATIONS

* Equal contribution # Mentored

	BIRD-Interact: Re-imagining Text-to-SQL Evaluation via Lens of Dynamic Interactions Nan Huo, Xiaohan Xu, *Jinyang Li^#, Per Jacobsson, Shipei Lin, Bowen Qin, Binyuan Hui, Xiaolong Li, Ge Qu, Shuzheng Si, Linheng Han, Edward Alexander, Xintong Zhu, Rui Qin, Ruihan Yu, Yiyao Jin, Feige Zhou, Weihao Zhong, Yun Chen, Hongyu Liu, Chenhao Ma, Fatma Ozcan, Yannis Papakonstantinou, Reynold Cheng Accepted to The Thirteenth International Conference on Learning Representations (ICLR Oral**), 2026. (1-1.5%)
	SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications Jinyang Li, Xiaolong Li, Ge Qu, Per Jacobsson, Bowen Qin, Binyuan Hui, Shuzheng Si, Nan Huo, Xiaohan Xu, Yue Zhang, Ziwei Tang, Yuanshuai Li, Florensia Widjaja, Xintong Zhu, Feige Zhou, Yongfeng Huang, Yannis Papakonstantinou, Fatma Ozcan, Chenhao Ma, Reynold Cheng Accepted to The Thirty-Nineth Annual Conference on Neural Information Processing Systems (NeurIPS Main*), 2025.
	Agents Help Agents: Unlocking SLM Potential for Data Analysis Code Generation via Non-Parametric Knowledge Distillation Jinyang Li, Jack Williams, Nick McKenna, Arian Askari, Nicholas Wilson, Reynold Cheng Accepted to The Thirty-Nineth Annual Conference on Neural Information Processing Systems (NeurIPS Main), 2025.
	SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQL Ge Qu, Jinyang Li^#, Bowen Qin, Xiaolong Li, Nan Huo, Chenhao Ma, Reynold Cheng The 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025.
	Micro-Act: Mitigate Knowledge Conflict in Question Answering via Actionable Self-Reasoning Nan Huo, Jinyang Li^#, Bowen Qin, Ge Qu, Xiaolong Li, Xiaodong Li, Chenhao Ma, Reynold Cheng The 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025.
	Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents Jinyang Li, Nan Huo, Yan Gao, Jiayi Shi, Yingxiu Zhao, Ge Qu, Bowen Qin, Yurong Wu, Xiaodong Li, Chenhao Ma, Jian-Guang Lou, Reynold Cheng Accepted to 42nd International Conference on Machine Learning (ICML), 2025.
	Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generation Ge Qu, Jinyang Li, Bowen Li, Bowen Qin, Nan Huo, Chenhao Ma, Reynold Cheng Accepted to 62nd Annual Meeting of the Association for Computational Linguistics (ACL Findings), 2024.
	A Survey on Knowledge Distillation of Large Language Models Xiaohan Xu, Ming Li, Chongyang Tao, Tao Shen, Reynold Cheng, Jinyang Li, Can Xu, Dacheng Tao, Tianyi Zhou Arxiv Preprint 2024.
	DevBench: A Comprehensive Benchmark for Software Development Bowen Li, Wenhan Wu, Ziwei Tang, Lin Shi, John Yang, Jinyang Li, Shunyu Yao, Chen Qian, Binyuan Hui, Qicheng Zhang, Zhiyin Yu, He Du, Ping Yang, Dahua Lin, Chao Peng, Kai Chen The Joint International Conference on Computational Linguistics (Coling), 2024.
	An Investigation of LLMs’ Inefficacy in Understanding Converse Relations Chengwen Qi, Bowen Li, Binyuan Hui, Bailin Wang, Jinyang Li, Jinwang Wu, Yuanjun Laili Accepted to The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP Main), 2023.
	Causal Document-Grounded Dialogue Pre-training Yingxiu Zhao, Bowen Yu, Haiyang Yu, Bowen Li, Jinyang Li, Cao Wang, Fei Huang, Yongbin Li, Nevin L. Zhang Accepted to The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP Main), 2023.
	Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs Jinyang Li, Binyuan Hui, Ge Qu, Binhua Li, Jiaxi Yang, Bowen Li, Bailin Wang, Bowen Qin, Rongyu Cao, Ruiying Geng, Nan Huo, Chenhao Ma, Kevin C.C. Chang, Fei Huang, Reynold Cheng, Yongbin Li Accepted to The Thirty-Seventh Annual Conference on Neural Information Processing Systems (NeurIPS Spotlight*), 2023.
	Two-stage Text-to-BIMQL Semantic Parsing for Building Information Model Extraction Using Graph Neural Networks Mengtian Yin, Llewellyn Tang, Chris Webster, Jinyang Li, Haotian Li, Zhuoquan Wu, Reynold C.K. Cheng Published in Automation in Construction 2023.
	A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions Bowen Qin, Binyuan Hui, Lihan Wang, Min Yang, Jinyang Li, Binhua Li, Ruiying Geng, Rongyu Cao, Jian Sun, Luo Si, Fei Huang, Yongbin Li Arxiv Preprint 2023.
	Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing Jinyang Li, Binyuan Hui, Reynold C.K.Cheng, Bowen Qin, Chenhao Ma, Nan Huo, Fei Huang, Wenyu Du, Luo Si, Yongbin Li Accepted to The 37th AAAI Conference on Artificial Intelligence (AAAI Oral) 2023.

Awards & Scholarships

Distinguished Reviewers, NeurIPS TRL, 2023
HKU Presidential PhD Scholar Programme (~ US $51,712/year), 2022-2025
Excellent Graduation Thesis in the Department of Electrical Engineering (Top 5%), 2017
Chinese Delegate in Youth Assembly at United Nations, 2014
National People's Scholarship, 2015, 2016, 2017
Excellent Presentation "Application of Quantitative Trading by Stop-Loss Strategy and Machine Learning" in Youth Leadership Training and Exchange Programs at the International Monetary Fund, 2014
Member of Harbin Institute of Technology Robotic Team, 2016, 2017
Excellent Design Award of 2016 Industrial Practice in Harbin Institute of Technology, 2016