Fuyang (Scott) Cui

Hi! I'm Scott, an undergraduate student at the University of Toronto. I'm fortunate to be supervised by Prof. Si Xujie and Prof. Sheila McIlraith. I'm also working in Jimmy Ba's group, guided by Silviu Pitis, Michael Zhang, Pashootan Vaezipoor, and more.

My primary research interest lies in deep learning, particularly reinforcement learning. To be more specific, my goal is to develop algorithms that can generalize effectively to complex environments with potentially multiple agents

Email: scottc[at]cs[dot]toronto[dot]edu

GitHub LinkedIn

profile photo

Research

I'm interested in reinforcement learning, deep learning, and language modeling.

* denotes equal contributions.

Report Cards: Qualitative Evaluation of Language Models Using Natural Language Summaries
Blair Yang*, Fuyang Cui*, Keiran Paster, Jimmy Ba, Pashootan Vaezipoor, Silviu Pitis, Michael R. Zhang
ArXiv
project page / arXiv

We propose metrics for qualitative evaluations of LLMs and methods for generating and assessing them.

Dreamitator: Dream and Imitate to Control
Yuhan Chen*, Fuyang Cui*, Shouyi Hung*, Liwei Yang*

Improved world model imagination accuracy by auxiliary imitating past actions.

Misc.

I love playing table tennis and building my body with all kinds of activities.

Webpage Source: Jon Barron