collaborators

6 papers

cs.AI2026

MMIR-TCM: Memory-Integrated Multimodal Inference and Retrieval for TCM Clinical Decision Support

Lihui Luo, Joongwon Chae, Ziyan Chen +13

Traditional Chinese Medicine (TCM) diagnosis, particularly through tongue inspection, faces persistent challenges in subjectivity and reproducibility. The application of multimodal…

cs.CL2025

Beyond Query-Level Comparison: Fine-Grained Reinforcement Learning for Text-to-SQL with Automated Interpretable Critiques

Guifeng Wang, Yuanfeng Song, Meng Yang +3

Text-to-SQL, a pivotal natural language processing (NLP) task that converts textual queries into executable SQL, has seen substantial progress in recent years. However, existing ev…

cs.AI2025

DataSage: Multi-agent Collaboration for Insight Discovery with External Knowledge Retrieval, Multi-role Debating, and Multi-path Reasoning

Xiaochuan Liu, Yuanfeng Song, Xiaoming Yin +1

In today's data-driven era, fully automated end-to-end data analytics, particularly insight discovery, is critical for discovering actionable insights that assist organizations in…

cs.CL2025

Beyond SELECT: A Comprehensive Taxonomy-Guided Benchmark for Real-World Text-to-SQL Translation

Hao Wang, Yuanfeng Song, Xiaoming Yin +1

Text-to-SQL datasets are essential for training and evaluating text-to-SQL models, but existing datasets often suffer from limited coverage and fail to capture the diversity of rea…

cs.DB2025

UniDataBench: Evaluating Data Analytics Agents Across Structured and Unstructured Data

Han Weng, Zhou Liu, Yuanfeng Song +3

In the real business world, data is stored in a variety of sources, including structured relational databases, unstructured databases (e.g., NoSQL databases), or even CSV/excel fil…

cs.LG2025

Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward

Han Weng, Puzhen Wu, Longjie Cui +10

Reinforcement learning (RL) has been widely adopted to enhance the performance of large language models (LLMs) on Text-to-SQL tasks. However, existing methods often rely on executi…