Fuyuan Lyu

Even state-of-the-art vision-language models frequently lie and hallucinate when playing social deduction games, raising serious questions about their reliability in real-world applications requiring grounded reasoning.

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.