Research

I am broadly interested in the general area of Artificial Intelligence, with emphasis on Large Language Model (LLM) Alignment, LLM Scalable Oversight, and Multi-modal LLMs. I derive great delight from solving challenging problems in these areas!

Herbert A. Simon said that human intelligence is just the rule-governed manipulation of symbols. I believe one day machines could achieve the same capacity of human’s intelligence. I dream to dedicate myself to this challenge and to make human life better. But “of course, AI itself is just part of a grander scheme driving the universe from simple initial conditions to more and more unfathomable complexity. Finally, even this awesome process may be just a tiny part of the even grander, optimally efficient computation of all logically possible universes.”