7 citations · 15 across the 5 of their papers we have counts for
6 papers
DualSQL: Text-to-SQL with Multi-Agent Reinforcement Learning
Shijie Chen, Yu Gan, Yeounoh Chung +6
State-of-the-art Text-to-SQL systems are typically multi-agent pipelines centered around two fundamental tasks: schema linking and SQL generation. However, existing work trains sep…
Mixture-of-Experts with Gradient Conflict-Driven Subspace Topology Pruning for Emergent Modularity
Yuxing Gan, Ziyu Lei
Mixture-of-Experts (MoE) architectures achieve parameter efficiency through conditional computation, yet contemporary designs suffer from two fundamental limitations: structural pa…
Is it Bigger than a Breadbox: Efficient Cardinality Estimation for Real World Workloads
Zixuan Yi, Sami Abu-el-Haija, Yawen Wang +8
DB engines produce efficient query execution plans by relying on cost models. Practical implementations estimate cardinality of queries using heuristics, with magic numbers tuned t…
Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQL
Yeounoh Chung, Gaurav T. Kakkar, Yu Gan +2
Large Language Models (LLMs) have demonstrated impressive capabilities across a range of natural language processing tasks. In particular, improvements in reasoning abilities and t…
CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL
Mohammadreza Pourreza, Hailong Li, Ruoxi Sun +7
In tackling the challenges of large language model (LLM) performance for Text-to-SQL tasks, we introduce CHASE-SQL, a new framework that employs innovative strategies, using test-t…
CardBench: A Benchmark for Learned Cardinality Estimation in Relational Databases
Yannis Chronis, Yawen Wang, Yu Gan +4
Cardinality estimation is crucial for enabling high query performance in relational databases. Recently learned cardinality estimation models have been proposed to improve accuracy…