Zilong Wang

Welcome! I am a fifth-year PhD student at UC San Diego advised by Prof. Jingbo Shang. I spent wonderful time doing research at Amazon Foundation Modl, Google Cloud AI, Google DeepMind, Google Research, Adobe Research, and Microsoft Research Asia. I received my B.S. in Computer Science from Peking University in 2020, where I was advised by Prof. Xiaojun Wan.

My research centers on leveraging language models for reasoning and planning, with a focus on: (1) LLM + Retrieval: Enhancing factual accuracy and minimizing hallucinations through retrieval-augmented generation (RAG). (2) LLM + Code: Improving the automatic debugging capabilities and coding proficiency of language models. (3) LLM + Multimodal: Empowering language models to tackle multimodal tasks via autonomous agents, such as table-based reasoning and visually-rich document extraction.

My earlier research forcused on visually-rich document understanding, where I enabled language models to encode multimodal features and understand the rich contents in documents of various formats, such as forms, receipts, web pages, etc.