About Me

I am a Postdoctoral Research Fellow at Hong Kong Catastrophic Risk Centre (HKCRC), Lingnan University. I received my PhD from the University of Hong Kong (HKU) under the supervision of David McCarthy, and my MPhil from Lingnan University under the supervision of Jiji Zhang and Simon Goldstein.

My research is motivated by a broad question: how should rational agents learn from new information under uncertainty? Rational agents continually acquire new information, form and revise beliefs, and make decisions in light of an ever-changing body of evidence. Understanding the epistemic principles that govern these processes—and how rational belief should guide rational action—lies at the center of my work in formal epistemology and decision theory.

Much of my recent research investigates these questions through the lens of conservative belief revision within Bayesian epistemology. I develop formal models of minimal change, asking which aspects of an agent’s prior epistemic state ought to be preserved, how competing preservation requirements should be balanced, and why different informational contexts call for different principles of rational revision. My work combines axiomatic methods with divergence-based approaches to characterize, compare, and evaluate competing models of rational belief change.

More broadly, I am interested in the relationship between epistemic rationality and rational choice. I study how principles governing belief formation and revision shape rational decision-making under uncertainty, and how normative theories of choice can in turn illuminate the foundations of rational learning.

I am also interested in how these questions extend from human to artificial reasoning. Modern AI systems likewise learn from information, construct internal representations of the world, and make decisions under uncertainty, raising many of the same foundational questions concerning belief, representation, explanation, and rational agency. I am particularly interested in what modern deep learning systems reveal about machine reasoning, how learned representations should be understood from an epistemological perspective, and how decision-theoretic ideas can help clarify foundational concepts in artificial intelligence, including intelligence and preference-based approaches to AI alignment.

I am always happy to discuss research ideas and ongoing projects. Please feel free to contact me at maomeiwang@ln.edu.hk.

Here is my CV.