Tengyang Xie comes to UW-Madison from a postdoctoral position at Microsoft Research, New England and New York City Lab. His research goal is “to unlock seemingly impossible capabilities through reinforcement learning.” Surprised by the amount of snow on his first visit to campus, Xie looks forward to exploring winter activities on the frozen lakes!
Hometown:
Shijiazhuang, China
Educational/professional background:
I completed my PhD in Computer Science at the University of Illinois at Urbana-Champaign. Before starting as faculty, I was a postdoc at Microsoft Research, New England lab and New York City lab.
How did you get into your field of research?
I work in the field of artificial intelligence (AI). I’ve been fascinated by techniques that teach machines to mimic human intelligence since my undergraduate years. I also love math and physics and enjoy gaining a deep understanding of mathematical principles behind the techniques. This passion drives my research in AI, especially from a theoretical perspective.
What are your areas of focus?
I have a broad interest in artificial intelligence and machine learning, with a particular focus on reinforcement learning (RL). It teaches machines to reason and make decisions like humans, through interaction with the environment. I believe RL is one of the most crucial components for achieving human-like AI systems. My research aims to unlock seemingly impossible capabilities through reinforcement learning, driving progress towards this ambitious long-term goal.
What main issue do you address or problem do you seek to solve in your work?
I am currently focused on three highly connected problems: 1) emerging interactive learning paradigms (esp. those related to RL) with/for large language models (LLMs); 2) the mathematical principles of reinforcement learning and decision-making; and 3) the algorithm and system challenges of scaling up new modalities.
What’s one thing you hope students who take a class with you will come away with?
I am teaching a machine learning class, which is an interesting and broad topic. I hope students come away with knowledge of either the theory, algorithms, or applications of machine learning (or all of them!).
What attracted you to UW-Madison?
UW-Madison has a very strong computer science department, as well as a very strong research community across most research areas. UW-Madison also has many respected researchers, and it’s my honor to become their colleague! In addition, I really like this beautiful city.
What was your first visit to campus like?
My first visit to the campus was in late March. Madison had just had a heavy snow, and I was a little surprised even as a person who had been living in the north for years. But soon after that, I was impressed with the beauty of the campus.
What are you looking forward to doing or experiencing in Madison?
I have already been looking forward to the winter activities on frozen lakes! Moreover, the aurora!
Hobbies/other interests:
Table tennis, history