helen writes, helen thinks, helen builds, helen sits under a tomato tree

Hi! I am Helen Hui, a CS undergrad at Princeton University doing research on...

• Agent swarms, VLMs & alignment @ Princeton Language and Intelligence Lab with Professor Sanjeev Arora
• Peer prediction theory & alignment @ Google DeepMind Princeton with Professor Elad Hazan

I am interested in alignment, nonverifiable rewards, and continual learning systems. Previously, I worked on memory at Memories.ai.