papers

Publications (40)

cs.DB2026

TACO: A Benchmark for Open-Domain Text-to-SQL with Ambiguous and Cross-Database Queries

Chao Deng, Ju Fan, Yuyu Luo +7

Text-to-SQL aims to translate natural language questions into executable SQL queries over structured databases. Existing benchmarks mainly focus on closed-domain settings with pred…

cs.CL2023

Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation

Zihui Gu, Ju Fan, Nan Tang +7

Zero-shot NL2SQL is crucial in achieving natural language to SQL that is adaptive to new environments (e.g., new databases, new linguistic phenomena or SQL structures) with zero an…

cs.LG2026

TANDEM: Bi-Level Data Mixture Optimization with Twin Networks

Jiaxing Wang, Deping Xiang, Jin Xu +9

The capabilities of large language models (LLMs) significantly depend on training data drawn from various domains. Optimizing domain-specific mixture ratios can be modeled as a bi-…

cs.CL2025

AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Framework

Meihao Fan, Ju Fan, Nan Tang +3

Answering natural language (NL) questions about tables, known as Tabular Question Answering (TQA), is crucial because it allows users to quickly and efficiently extract meaningful…

cs.DB2020

Relational Data Synthesis using Generative Adversarial Networks: A Design Space Exploration

Ju Fan, Tongyu Liu, Guoliang Li +3

The proliferation of big data has brought an urgent demand for privacy-preserving data publishing. Traditional solutions to this demand have limitations on effectively balancing th…

cs.AI2026

Reasoning and Tool-use Compete in Agentic RL:From Quantifying Interference to Disentangled Tuning

Yu Li, Mingyang Yi, Xiuyu Li +6

Agentic Reinforcement Learning (ARL) trains large language models to interleave reasoning with external tool execution to solve complex tasks. Most existing ARL methods train a sin…

cs.LG2026

ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment

Xiuyu Li, Jinkai Zhang, Mingyang Yi +4

Reinforcement Learning (RL) post-training alignment for language models is effective, but also costly and unstable in practice, owing to its complicated training process. To addres…

cs.DB2024

Auto-Formula: Recommend Formulas in Spreadsheets using Contrastive Learning for Table Representations

Sibei Chen, Yeye He, Weiwei Cui +5

Spreadsheets are widely recognized as the most popular end-user programming tools, which blend the power of formula-based computation, with an intuitive table-based interface. Toda…

cs.DB2018

Crowd-Powered Data Mining

Chengliang Chai, Ju Fan, Guoliang Li +2

Many data mining tasks cannot be completely addressed by auto- mated processes, such as sentiment analysis and image classification. Crowdsourcing is an effective way to harness th…

cs.CL2022

PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training

Zihui Gu, Ju Fan, Nan Tang +3

Fact verification has attracted a lot of research attention recently, e.g., in journalism, marketing, and policymaking, as misinformation and disinformation online can sway one's o…

cs.DB2025

TAIJI: MCP-based Multi-Modal Data Analytics on Data Lakes

Chao Zhang, Shaolei Zhang, Quehuan Liu +3

The variety of data in data lakes presents significant challenges for data analytics, as data scientists must simultaneously analyze multi-modal data, including structured, semi-st…

cs.AI2024

Large Language Model for Table Processing: A Survey

Weizheng Lu, Jing Zhang, Ju Fan +3

Tables, typically two-dimensional and structured to store large amounts of data, are essential in daily activities like database queries, spreadsheet manipulations, web table quest…

cs.AI2024

Harnessing Diversity for Important Data Selection in Pretraining Large Language Models

Chi Zhang, Huaping Zhong, Kuan Zhang +10

Data selection is of great significance in pre-training large language models, given the variation in quality within the large-scale available training corpora. To achieve this, re…

cs.DB2026

A Survey of Data Agents: Emerging Paradigm or Overstated Hype?

Yizhang Zhu, Liangwei Wang, Chenyu Yang +22

The rapid advancement of large language models (LLMs) has spurred the emergence of data agents, autonomous systems designed to orchestrate Data + AI ecosystems for tackling complex…

cs.DB2023

ChatPipe: Orchestrating Data Preparation Program by Optimizing Human-ChatGPT Interactions

Sibei Chen, Hanbing Liu, Weiting Jin +5

Orchestrating a high-quality data preparation program is essential for successful machine learning (ML), but it is known to be time and effort consuming. Despite the impressive cap…

cs.AI2024

Diverse and Fine-Grained Instruction-Following Ability Exploration with Synthetic Data

Zihui Gu, Xingwu Sun, Fengzong Lian +3

Instruction-following is particularly crucial for large language models (LLMs) to support diverse user requests. While existing work has made progress in aligning LLMs with human p…

cs.DB2025

Automatic Database Configuration Debugging using Retrieval-Augmented Language Models

Sibei Chen, Ju Fan, Bin Wu +8

Database management system (DBMS) configuration debugging, e.g., diagnosing poorly configured DBMS knobs and generating troubleshooting recommendations, is crucial in optimizing DB…

cs.DB2025

A Unified Model for Cardinality Estimation by Learning from Data and Queries via Sum-Product Networks

Jiawei Liu, Ju Fan, Tongyu Liu +5

Cardinality estimation is a fundamental component in database systems, crucial for generating efficient execution plans. Despite advancements in learning-based cardinality estimati…

cs.DB2024

A Plug-and-Play Natural Language Rewriter for Natural Language to SQL

Peixian Ma, Boyan Li, Runzhi Jiang +3

Existing Natural Language to SQL (NL2SQL) solutions have made significant advancements, yet challenges persist in interpreting and translating NL queries, primarily due to users' l…

cs.DB2026

RaG-Tree: Combining R-Tree and HNSW for Multi-Attribute Range Filtered Approximate Nearest Neighbor Search

Jiawei Liu, Xiang Zhang, Chao Zhang +2

Multi-attribute range-filtered approximate nearest neighbor search (MR-ANNS), which retrieves high-dimensional vectors satisfying multiple attribute constraints, is a fundamental o…

cs.LG2021

RPT: Relational Pre-trained Transformer Is Almost All You Need towards Democratizing Data Preparation

Nan Tang, Ju Fan, Fangyi Li +5

Can AI help automate human-easy but computer-hard data preparation tasks that burden data scientists, practitioners, and crowd workers? We answer this question by presenting RPT, a…

cs.CV2026

OFA-Diffusion Compression: Compressing Diffusion Model in One-Shot Manner

Haoyang Jiang, Zekun Wang, Mingyang Yi +6

The Diffusion Probabilistic Model (DPM) achieves remarkable performance in image generation, while its increasing parameter size and computational overhead hinder its deployment in…

cs.CV2026

Fragile Reconstruction: Adversarial Vulnerability of Reconstruction-Based Detectors for Diffusion-Generated Images

Haoyang Jiang, Mingyang Yi, Shaolei Zhang +4

Recently, detecting AI-generated images produced by diffusion-based models has attracted increasing attention due to their potential threat to safety. Among existing approaches, re…

cs.DB2012

SEAL: Spatio-Textual Similarity Search

Ju Fan, Guoliang Li, Lizhu Zhou +2

Location-based services (LBS) have become more and more ubiquitous recently. Existing methods focus on finding relevant points-of-interest (POIs) based on users' locations and quer…

cs.DB2026

Data Agents: Levels, State of the Art, and Open Problems

Yuyu Luo, Guoliang Li, Ju Fan +1

Data agents are an emerging paradigm that leverages large language models (LLMs) and tool-using agents to automate data management, preparation, and analysis tasks. However, the te…

cs.DB2026

DA-Studio: An Agentic System for End-to-End Data Analysis

Yizhe Liu, Shaolei Zhang, Ju Fan

Real-world data analysis is a multi-step process over heterogeneous inputs rather than merely producing a final answer. A practical system should autonomously organize multi-step w…

cs.DB2024

SEED: Domain-Specific Data Curation With Large Language Models

Zui Chen, Lei Cao, Sam Madden +7

Data curation tasks that prepare data for analytics are critical for turning data into actionable insights. However, due to the diverse requirements of applications in different do…

cs.DB2026

DeepPrep: An LLM-Powered Agentic System for Autonomous Data Preparation

Meihao Fan, Ju Fan, Yuxin Zhang +7

Data preparation, which aims to transform heterogeneous and noisy raw tables into analysis-ready data, remains a major bottleneck in data science. Recent approaches leverage large…

cs.CL2023

Cost-Effective In-Context Learning for Entity Resolution: A Design Space Exploration

Meihao Fan, Xiaoyue Han, Ju Fan +4

Entity resolution (ER) is an important data integration task with a wide spectrum of applications. The state-of-the-art solutions on ER rely on pre-trained language models (PLMs),…

cs.CL2026

Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards

Yuxin Zhang, Meihao Fan, Ju Fan +5

Recent advances in large language models (LLMs) trained with reinforcement learning (RL) have improved Text-to-SQL performance. However, RL-based approaches still struggle with com…

cs.DB2025

PBench: Workload Synthesizer with Real Statistics for Cloud Analytics Benchmarking

Yan Zhou, Chunwei Liu, Bhuvan Urgaonkar +11

Cloud service providers commonly use standard benchmarks like TPC-H and TPC-DS to evaluate and optimize cloud data analytics systems. However, these benchmarks rely on fixed query…

cs.CL2024

CodeS: Towards Building Open-source Language Models for Text-to-SQL

Haoyang Li, Jing Zhang, Hanbing Liu +7

Language models have shown promising performance on the task of translating natural language questions into SQL queries (Text-to-SQL). However, most of the state-of-the-art (SOTA)…

cs.AI2025

DeepAnalyze: Agentic Large Language Models for Autonomous Data Science

Shaolei Zhang, Ju Fan, Meihao Fan +2

Autonomous data science, from raw data sources to analyst-grade deep research reports, has been a long-standing challenge, and is now becoming feasible with the emergence of powerf…

cs.DB2023

VerifAI: Verified Generative AI

Nan Tang, Chenyu Yang, Ju Fan +3

Generative AI has made significant strides, yet concerns about the accuracy and reliability of its outputs continue to grow. Such inaccuracies can have serious consequences such as…

cs.DB2025

A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?

Xinyu Liu, Shuyu Shen, Boyan Li +7

Translating users' natural language queries (NL) into SQL queries (i.e., Text-to-SQL, a.k.a. NL2SQL) can significantly reduce barriers to accessing relational databases and support…

cs.SI2018

Influential User Subscription on Time-Decaying Social Streams

Xin Yang, Ju Fan

Influence maximization which asks for -size seed set from a social network such that maximizing the influence over all other users (called influence spread) has widely attracted…

eess.AS2022

Contextual Expressive Text-to-Speech

Jianhong Tu, Zeyu Cui, Xiaohuan Zhou +4

The goal of expressive Text-to-speech (TTS) is to synthesize natural speech with desired content, prosody, emotion, or timbre, in high expressiveness. Most of previous studies atte…

cs.DB2026

DataEvolver: Automatic Data Preparation for Large Language Models through Multi-Level Self-Evolving

Chao Deng, Shaolei Zhang, Ju Fan +1

High-quality training data is essential to large language models (LLMs) and typically requires extensive and costly manual curation. Existing automatic data preparation methods rel…

cs.DB2025

Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search

Boyan Li, Jiayi Zhang, Ju Fan +4

Text-to-SQL, which enables natural language interaction with databases, serves as a pivotal method across diverse industries. With new, more powerful large language models (LLMs) e…

cs.AI2026

CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks?

Yuxin Zhang, Ju Fan, Meihao Fan +2

Advanced agents are increasingly demonstrating the potential to operate as autonomous engineers, creating a growing demand for evaluation benchmarks that capture the complexity of…