Xiuqiang He

Fine-tuning LLMs with a data-driven pipeline that incorporates real user queries and a new augmentation method (AugFC) dramatically improves function calling performance in online financial QA systems.

Forget retraining: ReAd dynamically adapts deployed sequential recommendation models to real-time preference shifts by retrieving and integrating collaborative user preference signals at test time.

Separating long-term preferences from short-term intentions via self-supervision boosts session-based recommendation, outperforming standard fusion methods.