collaborators

5 papers

cs.AI2026

UniQL: Towards Dialect-Universal Benchmarking for Text-to-SQL

Jianling Gao, Chongyang Tao, Jiayuan Bai +7

Existing text-to-SQL benchmarks are largely centered on SQLite, making it difficult to evaluate whether models can generalize across heterogeneous SQL dialects. However, real-world…

cs.CL2026

EvolSQL: Structure-Aware Evolution for Scalable Text-to-SQL Data Synthesis

Xuanguang Pan, Chongyang Tao, Jiayuan Bai +5

Training effective Text-to-SQL models remains challenging due to the scarcity of high-quality, diverse, and structurally complex datasets. Existing methods either rely on limited h…

cs.CL2026

NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents

Jingzhe Ding, Shengda Long, Changxin Pu +46

Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks fail to rigorously evaluate the long-horizon capabilities re…

cs.CL2025

AIR: Post-training Data Selection for Reasoning via Attention Head Influence

Jinrui Liu, Jeff Wu, Xuanguang Pan +3

LLMs achieve remarkable multi-step reasoning capabilities, yet effectively transferring these skills via post-training distillation remains challenging. Existing data selection met…

cs.AI2025

JudgeSQL: Reasoning over SQL Candidates with Weighted Consensus Tournament

Jiayuan Bai, Xuan-guang Pan, Chongyang Tao +1

Text-to-SQL is a pivotal task that bridges natural language understanding and structured data access, yet it remains fundamentally challenging due to semantic ambiguity and complex…