JF
Ju Fan
cs.DBcs.AIcs.CLcs.LGcs.CVcs.HCBetacoronaviruscoronavirusCoronavirus InfectionsCOVID-19
On Valency
published · living versionsW_3wktyacd·v1 · currentpublished
Cleaning or Recalling? Knowledge Dependence in LLM-based Data Cleaning [Experiment, Analysis & Benchmark]
with Jingru Yang, Honglu Zhang, Jiayi Mi, Zheng Chen +1
1 version
Preprints & journals
33 papers in the corpus · 2012–2026DA-Studio: An Agentic System for End-to-End Data Analysis2606.31423v1 · Yizhe Liu, Shaolei Zhang, Ju Fan2026 · 0 citationsarXiv
TACO: A Benchmark for Open-Domain Text-to-SQL with Ambiguous and Cross-Database Queries2606.14201v1 · Chao Deng, Ju Fan, Yuyu Luo et al.2026 · 1 citationarXiv
TANDEM: Bi-Level Data Mixture Optimization with Twin Networks2606.04401v1 · Jiaxing Wang, Deping Xiang, Jin Xu et al.2026 · 0 citationsarXiv
OFA-Diffusion Compression: Compressing Diffusion Model in One-Shot Manner2604.12668v1 · Haoyang Jiang, Zekun Wang, Mingyang Yi et al.2026 · 0 citationsarXiv
Fragile Reconstruction: Adversarial Vulnerability of Reconstruction-Based Detectors for Diffusion-Generated Images2604.12781v1 · Haoyang Jiang, Mingyang Yi, Shaolei Zhang et al.2026 · 0 citationsarXiv
DeepPrep: An LLM-Powered Agentic System for Autonomous Data Preparation2602.07371v1 · Meihao Fan, Ju Fan, Yuxin Zhang et al.2026 · 0 citationsarXiv
Data Agents: Levels, State of the Art, and Open Problems2602.04261v1 · Yuyu Luo, Guoliang Li, Ju Fan et al.2026 · 2 citationsSIGMOD 2026 Tutorial
Reasoning and Tool-use Compete in Agentic RL:From Quantifying Interference to Disentangled Tuning2602.00994v3 · Yu Li, Mingyang Yi, Xiuyu Li et al.2026 · 0 citationsarXiv
ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment2601.21484v3 · Xiuyu Li, Jinkai Zhang, Mingyang Yi et al.2026 · 0 citationsarXiv
DeepAnalyze: Agentic Large Language Models for Autonomous Data Science2510.16872v1 · Shaolei Zhang, Ju Fan, Meihao Fan et al.2025 · 3 citationsarXiv
PBench: Workload Synthesizer with Real Statistics for Cloud Analytics Benchmarking2506.16379v1 · Yan Zhou, Chunwei Liu, Bhuvan Urgaonkar et al.2025 · 10 citationsarXiv
Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards2505.04671v3 · Yuxin Zhang, Meihao Fan, Ju Fan et al.2025 · 2 citationsarXiv
Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search2502.17248v2 · Boyan Li, Jiayi Zhang, Ju Fan et al.2025 · 1 citationarXiv
A Plug-and-Play Natural Language Rewriter for Natural Language to SQL2412.17068v1 · Peixian Ma, Boyan Li, Runzhi Jiang et al.2024 · 1 citationarXiv
Automatic Database Configuration Debugging using Retrieval-Augmented Language Models2412.07548v2 · Sibei Chen, Ju Fan, Bin Wu et al.2024 · 12 citationsarXiv
AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Framework2412.10422v4 · Meihao Fan, Ju Fan, Nan Tang et al.2024 · 6 citationsarXiv
A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?2408.05109v7 · Xinyu Liu, Shuyu Shen, Boyan Li et al.2024 · 69 citationsTKDE July 2025
Diverse and Fine-Grained Instruction-Following Ability Exploration with Synthetic Data2407.03942v1 · Zihui Gu, Xingwu Sun, Fengzong Lian et al.2024 · 0 citationsAAAI 2024
Auto-Formula: Recommend Formulas in Spreadsheets using Contrastive Learning for Table Representations2404.12608v1 · Sibei Chen, Yeye He, Weiwei Cui et al.2024 · 4 citationsarXiv
CodeS: Towards Building Open-source Language Models for Text-to-SQL2402.16347v1 · Haoyang Li, Jing Zhang, Hanbing Liu et al.2024 · 134 citationsarXiv
Large Language Model for Table Processing: A Survey2402.05121v3 · Weizheng Lu, Jing Zhang, Ju Fan et al.2024 · 57 citationsarXiv
Cost-Effective In-Context Learning for Entity Resolution: A Design Space Exploration2312.03987v1 · Meihao Fan, Xiaoyue Han, Ju Fan et al.2023 · 44 citationsarXiv
SEED: Domain-Specific Data Curation With Large Language Models2310.00749v3 · Zui Chen, Lei Cao, Sam Madden et al.2023 · 9 citationsarXiv
VerifAI: Verified Generative AI2307.02796v2 · Nan Tang, Chenyu Yang, Ju Fan et al.2023 · 12 citationsarXiv
Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation2306.08891v1 · Zihui Gu, Ju Fan, Nan Tang et al.2023 · 6 citationsarXiv
ChatPipe: Orchestrating Data Preparation Program by Optimizing Human-ChatGPT Interactions2304.03540v1 · Sibei Chen, Hanbing Liu, Weiting Jin et al.2023 · 1 citationarXiv
Contextual Expressive Text-to-Speech2211.14548v1 · Jianhong Tu, Zeyu Cui, Xiaohuan Zhou et al.2022 · 2 citationsarXiv
PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training2211.02816v1 · Zihui Gu, Ju Fan, Nan Tang et al.2022 · 23 citationsarXiv
Online Health Information Seeking Using "#COVID-19 Patient Seeking Help" on Weibo in Wuhan, China: Descriptive Study.33001838 · Zhao, Xiaoman, Fan, Ju, Basnyat, Iccha et al.2020 · 115 citationsJournal of medical Internet research. 2020;22(10):e22910
Relational Data Synthesis using Generative Adversarial Networks: A Design Space Exploration2008.12763v1 · Ju Fan, Tongyu Liu, Guoliang Li et al.2020 · 11 citationsarXiv
Crowd-Powered Data Mining1806.04968v2 · Chengliang Chai, Ju Fan, Guoliang Li et al.2018 · 6 citationsarXiv
Influential User Subscription on Time-Decaying Social Streams1802.05305v1 · Xin Yang, Ju Fan2018 · 2 citationsarXiv
SEAL: Spatio-Textual Similarity Search1205.6694v1 · Ju Fan, Guoliang Li, Lizhu Zhou et al.2012 · 11 citationsProceedings of the VLDB Endowment (PVLDB), Vol. 5, No. 9, pp. 824-835 (2012)
Career total: 144 works. 33 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.