Yuxuan (Effie) Li

I am a Senior Research Scientist at Google DeepMind. I am broadly interested in machine and human intelligence, with a recent focus on human-AI communication, alignment, AI safety, and human growth. Some of my recent public work explores visual communication (including visual prompt engineering), fuzzy/miscommunication, and subtle communication between humans and AI systems.

I also work on mechanistic interpretability (in-context representations and structured computation in transformers) and human cognition. I also spent time on social intelligence benchmarking and embodied AI as interns at Meta and AI2, and built neural decoders of human episodic memory at UPenn.

Github  | CV  | Google Scholar  | Linkedin