Quoc Viet Hung Nguyen

Personalizing item selection during denoising boosts recommendation accuracy by leveraging user interactions more effectively than traditional methods.

FLEXRec shows that compact LLMs can achieve state-of-the-art recommendation accuracy without the computational burden of larger models.

LLM agents can conquer complex Text-to-SQL by creating intermediate "agentic views" that break down queries and filter schemas, achieving state-of-the-art results on challenging benchmarks.

FusionSQL lets you evaluate Text2SQL models on new databases without any labels, saving time and money while ensuring quality.