activity
20242026
most citedCHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL

7 citations · 14 across the 4 of their papers we have counts for

collaborators

7 papers

math.AP2026

Monomial Moving Zeros for the Heat Semigroup: An Explicit Finite-Order Differential Hierarchy

Gerardo Hernandez-del-Valle

Let $P_t=\exp(t\D^2/2)$ be the heat semigroup. For every integer and parameter $ρ\in\C$, we construct an entire function whose heat evolution has the prescribed…

cs.DB2026

The Case for TPU-Accelerated Analytical Query Processing

Yeounoh Chung, Jaehyun Ha, Helena Caminal +4

Large-scale analytical query processing requires computing substrates capable of immense distributed scale-out. Tensor Processing Units (TPUs) perfectly embody this extreme-scale a…

cs.CL2026

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…

cs.DB2026

AI Query Compilation for Unified and Optimized Execution

Yeounoh Chung, Helena Caminal, Fatma Ozcan

In this vision paper, we propose a novel architectural paradigm for accelerated AI query execution via a unified compiled execution strategy. By compiling the hybrid AI Query as a…

cs.DB2026

An Agentic Approach to Metadata Reasoning

Jiani Zhang, Sercan O. Arik, Cosmin Arad +2

As autonomous LLM agents evolve to perform complex analytical tasks that require integrating multiple datasets, the problem of discovering relevant data sources becomes a key bottl…

cs.DB2025★ 7 cited

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…

cs.LG2024★ 7 cited

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…