Complex AI Systems

Code Intelligence

LLM-powered code understanding and generation

Active Research

Overview

Research on leveraging LLMs for code-related tasks. SQL-of-Thought introduces a multi-agent framework for text-to-SQL with guided error correction, achieving state-of-the-art results on Spider. LoRACode uses parameter-efficient fine-tuning for code embeddings, reducing trainable parameters to under 2%.

Related Publications

SQL-of-Thought (DL4C @ NeurIPS 2025)
LoRACode (DL4C @ ICLR 2025)