Yao Tong

I am Yao Tong (童遥), a Ph.D. student in Computer Science at the National University of Singapore, supervised by Prof. Reza Shokri. I am currently a visiting researcher at ETH Zurich (SPY Lab), working with Prof. Florian Tramer. I received my B.E. in Computer Science and Engineering from The Chinese University of Hong Kong, Shenzhen, where I was advised by Prof. Baoyuan Wu, who inspired my first steps into research.

My research focuses on understanding and building controllable, user-centered AI systems. I study how to interpret, evaluate, and govern the behavior of AI systems, and how to identify and mitigate their privacy, security, and safety risks. My recent interests center on agent memory and personalization systems, especially the risks and control challenges that arise when AI agents remember, adapt to, and act on behalf of users.

My previous work spans several related themes:

• Understanding and interpreting model behaviors and capabilities. I study phenomena such as intrinsic biases and generalization, and how they are shaped by different stages of the learning pipeline, including model initialization, data distributions, training paradigms, and inference-time methods.
• Data and model provenance. How behavioral signals can support model fingerprinting, model lineage detection, copyright-related auditing, and data usage auditing, turning model properties into tools for attribution and protection.
• Controllability and alignment in interactive agents. How agents that remember, personalize, and adapt to users can remain controllable, auditable, and aligned with user intent.