XIFENG YAN |
home | publications | tutorials | dataset | software |
|
|||
|
Professor
Ph.D. (2006) |
Computer Science Department
Direction |
I am a professor at the University of California at Santa Barbara. The primary objective of my
research is to explore foundation
models in artificial intelligence, leveraging these models for knowledge
discovery, and developing cross-disciplinary applications in areas like
finance, healthcare, and science. We have extensively innovated on graph mining, graph
data management and pioneered
transformer-based time series
forecasting. I am also a co-inventor of
ADL/Mica (and its studio PromptDialog), an
agent first approach to conversational AI assistants. News (April 2025): We introduce ADL, a Declarative Language for Agent-Based Chatbots. ADL simplifies chatbot development by using natural language programming at its core, offering a declarative way to define agents and their interactions. News (March 2025): Mica (Multiple Intelligent Conversational Agents) is now live on Github. After years of exploring the ideal architecture for customer service bots, we finally arrived at a solution that we are satisfied with. It is a kind of YAML version of OpenAI's Swarm (and OpenAI Agent SDK). However, it has an SQL-like mindset. Mica abstracts away implementation details, providing a succinct description of agents and their relationship, making systematic prompting engineering, testing and debugging possible in the future. Mica is developed by Sirui and me. News (Feb 2025): Our alumnus, Dr. Yu Su received 2025 Sloan Research Fellowship. News Archive |
||||
RESEARCH INTERESTS | ||||
|
||||
|
|
||||||||||
|
Last Modified: July 10, 2022