Yuxuan (Effie) Li

liyuxuan[at]google[dot]com
I am a Research Scientist at Google DeepMind. I am broadly interested in machine and human cognition, and the mechanisms that support these abilities in deep learning models and the human brain. Some of my recent works include evaluating zero-shot visual reasoning in video models and understanding in-context task representations in language models.
My PhD research investigated a learning theory of task decomposition in transformers and humans. I also worked on multi-modal LLM evaluation and embodied AI as interns at Meta and AI2, and spent time building neural decoders of human episodic memory at UPenn.
Github
| CV
| Google Scholar
| Linkedin