Boyan Li | 李伯岩

Boyan Li | 李伯岩🧑‍🚀

I am a second-year Ph.D. student at The Hong Kong University of Science and Technology (Guangzhou), supervised by Prof. Yuyu Luo. My research focuses on AI for Databases and Data Agents, exploring how language models can reason over complex data environments and serve as trustworthy, autonomous interfaces between people and data.

I enjoy building with Claude Code and Codex . I care about details, but never complexity for its own sake. To me, the best solutions are simple enough to explain, rigorous enough to trust, and useful enough to matter.

Email: bli303@connect.hkust-gz.edu.cn / CV / Twitter Google Scholar / GitHub

News

Jun. 2026 DataMagic was accepted to the VLDB 2026 Demo Track.

May 2026 I received the INFH Research Excellence Award (Merit Prize).

Apr. 2026 DPC and ROSE were accepted to ACL 2026 Main.

Mar. 2026 We are organizing the KDD Cup 2026 Data Agents competition.

Mar. 2026 Two DeepEye works—DeepEye-SQL and the DeepEye system demo—were accepted to SIGMOD 2026.

Mar. 2026 DeepEye won a Silver Medal at the 51st Geneva Inventions Exhibition.

Earlier news

Dec. 2025 I received a Research Excellence Award at the DSA Excellence Awards 2025.

Sep. 2025 nvBench 2.0 was accepted to NeurIPS 2025.

Jul. 2025 Three works were accepted: DeepVIS to IEEE VIS, our NL2SQL survey to IEEE TKDE, and EllieSQL to COLM.

May 2025 NL2SQL-BUGs and Alpha-SQL were accepted to KDD 2025 and ICML 2025.

Jan. 2025 HARVis was accepted to CHI 2025.

Jan. 2025 I received the Merit Prize for the 2024 DSA Excellent Research Award.

Sep. 2024 StatQA was accepted to NeurIPS 2024.

Jun. 2024 NL2SQL360 was accepted to VLDB 2024.

Publications

† Equal contribution. * Corresponding author.

If you would like to view my other publications, you are welcome to access them on my Google Scholar.

	DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces Boyan Li†, Zhuowen Liang†, Yupeng Xie†, Xiaotian Lin, Tianqi Luo, Xinyu Liu, Yizhang Zhu, Zhangyang Peng, Yuan Li, Zhengxuan Zhang, Jiayi Zhang, Nan Tang, Guoliang Li, Yuyu Luo* Paper / Code / Dataset / Leaderboard Preprint Official KDD Cup 2026 Benchmark A benchmark for data agents performing verifiable analytics across heterogeneous workspaces spanning structured files, databases, documents, and video.
	DPC: Training-Free Text-to-SQL Candidate Selection via Dual-Paradigm Consistency Boyan Li, Ou Ocean Kun Hei, Yue Yu, Yuyu Luo* Paper / Code ACL 2026 (Main, CCF-A) DPC selects reliable SQL candidates by verifying consistency between SQL and Python execution on adversarially synthesized, fully observable databases.
	ROSE: An Intent-Centered Evaluation Metric for NL2SQL Wenqi Pei†, Shizheng Hou†, Boyan Li†, Han Chen, Zhichao Shi, Yuyu Luo* Paper / Code ACL 2026 (Main, CCF-A) ROSE evaluates NL2SQL predictions against user intent rather than a single reference SQL, improving alignment with human judgment.
	DeepEye: A Steerable Self-driving Data Agent System Boyan Li, Yiran Peng, Yupeng Xie, Sirong Lu, Yizhang Zhu, Xing Mu, Xinyu Liu, Yuyu Luo* Paper / Homepage / Code SIGMOD 2026 (Demo, CCF-A) Silver Medal 51st Geneva International Exhibition of Inventions Best Open-source Project Award AI Agent 2025 Competition DeepEye orchestrates heterogeneous data and specialized tools as transparent, steerable workflows for trustworthy multimodal analytics.
	DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework Boyan Li, Chong Chen, Zhujun Xue, Yinan Mei, Yuyu Luo* Paper / Homepage / Code SIGMOD 2026 (CCF-A) Huawei Spark Award DeepEye-SQL treats Text-to-SQL as software engineering, integrating robust grounding, deterministic testing, and confidence-aware selection.
	DeepVIS: Bridging Natural Language and Data Visualization Through Step-wise Reasoning Zhihao Shuai†, Boyan Li†, Siyu Yan, Yuyu Luo, Weikai Yang* Paper / Code IEEE VIS 2025 (CCF-A) DeepVIS exposes step-wise NL2VIS reasoning, enabling users to inspect and refine how natural-language intent becomes a visualization.
	Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search Boyan Li, Jiayi Zhang, Ju Fan, Yanwei Xu, Chong Chen, Nan Tang, Yuyu Luo* Paper / Homepage / Code ICML 2025 (CCF-A) Deployed in Huawei Cloud DataArts Insight Deployed in Wuhan Urban Operation Agent Alpha-SQL uses Monte Carlo Tree Search to progressively construct and evaluate SQL queries, enabling strong zero-shot Text-to-SQL without fine-tuning.
	The Dawn of Natural Language to SQL: Are We Fully Ready? Boyan Li, Yuyu Luo, Chengliang Chai, Guoliang Li, Nan Tang Paper / Homepage / Code VLDB 2024 (CCF-A)* Top-2 Most Cited Paper Google Scholar (PVLDB 2024) NL2SQL360 evaluates Text-to-SQL methods across domains, SQL characteristics, and metrics to support scenario-specific model selection.

Experience

Tsinghua University · Database Group
Exchange Student · Jun. 2025 – Dec. 2025
Beijing, China
Mentored by Prof. Guoliang Li

Service and Teaching

General Chair: KDD Cup 2026 — Data Agents for Complex Data Analysis
Program Chair: VLDB 2026 Workshop on Agentic Data Systems
Reviewer: NeurIPS 2026, ICLR 2026, and IEEE TKDE
Invited Speaker: Huawei Squirrel Webinar — DeepEye-SQL, Jan. 2026
Teaching Assistant, HKUST(GZ): C++ Programming (UFUG 2601, Spring 2025–26); Table Representation Learning (DSAA 6000O, Spring 2024–25); Future Technology Exploration and Innovation Camp (Jul. 2026)

Honors and Awards

2026 Merit Prize, INFH Research Excellence Award
2026 Silver Medal, 51st Geneva International Exhibition of Inventions — DeepEye
2025 Research Excellence Award, DSA Excellence Awards, HKUST(GZ)
2025 Best Open-source Project Award, AI Agent 2025 Competition — DeepEye
2024 Merit Prize, DSA Excellent Research Award, HKUST(GZ)
2023 Highest Honors in Computer Science & Engineering and Outstanding Graduate, SUSTech
2022 Huawei Scholarship, Huawei Technologies
2020–22 Excellent Student Scholarship, SUSTech — three-time recipient
2020 National Encouragement Scholarship, Ministry of Education of China

✅复制完成

Keep Exploring