Anthony Peng

Hi, I'm Anthony, a CS PhD at Georgia Tech.

My research advances the safety alignment of generative foundation models by developing principled methods that make safety an intrinsic, generalizable property — so that models behave safely not only during training, but also when finetuned, reasoned over, or deployed autonomously in real-world settings.

My dissertation, advised by Polo Chau, has elevated foundational AI efforts across leading technology organizations, including Nvidia, Meta, IBM Research, Intel Lab, and ADP.

Say Hello

CV