Reynold Cheng

BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation via Lens of Dynamic Interactions

Orchestrating Pre-Trained Agents for Multi-Objective Decision Making

SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications

Unlocking SLM Potential for Data Analysis Code Generation via Non-Parametric Knowledge Distillation

Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis

Are Large Language Models Ready for Multi-Turn Tabular Data Analysis?

Benchmarking Intelligent LLM Agents for Conversational Data Analysis

Agents Help Agents: Exploring Training-Free Knowledge Distillation for Small Language Models in Data Science Code Generation