Research
Published papers and ongoing work. New projects are added here as they develop, before they're published.
Published
NeurIPS 2025 · DL4C workshop
SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction
A multi-agent framework that decomposes the Text2SQL task into schema linking, subproblem identification, query plan generation, SQL generation, and a guided correction loop. Unlike prior systems that rely only on execution-based static correction, we introduce taxonomy-guided dynamic error modification informed by in-context learning.
ICLR 2025 · DL4C workshop
LoRACode: LoRA Adapters for Code Embeddings
Introducing a novel method for finetuning code embedding models on code retrieval based on text and code queries, using low rank adapters, achieving substantial improvements on Mean Reciprocal Rank only on a small subset of trainable parameters.
