Master's at University of PennsylvaniaHi, this is Maggie! I am a first-year master's student at the University of Pennsylvania. I'm inspired by a picture where AI and human creativity come together to build a world powered by smart solutions. And I'd love to be one of the “little builders” crafting this bold, imaginative future.
On the "serious side", I like researching how humans and machines can make cooler decisions. On the "fun side", I am excited about building next-gen AI tools to facilitate us. For research, I'm an intern at Berkeley NLP Group guided by my amazing mentors Alane Suhr and Nicholas Tomlin. We explore how language agents can learn through interactions and collaborate for optimal decisions. In my free time, I also work on a real-time AI interview assistant called Beyz with my friends where I serve as Chief Scientist.
My research interest lies in the intersection of NLP and RL. Currently, I am particularly interested in how language can be used to guide the learning of agents in complex environments through interaction.
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
University of PennsylvaniaSchool of Engineering and Applied Science
Master of Science in EngineeringSep. 2024 - present
Selected Publications (view all )
World Models with Hints of Large Language Models for Goal Achieving
Zeyuan Liu*, Ziyu Huan*, Xiyao Wang, Jiafei Lyu, Jian Tao, Xiu Li, Furong Huang, Huazhe Xu (* equal contribution)
Under review. 2024
Inspired by human cognition, we propose a new multi-modal model-based RL approach named Dreaming with Large Language Models (DLLM).
World Models with Hints of Large Language Models for Goal Achieving
Zeyuan Liu*, Ziyu Huan*, Xiyao Wang, Jiafei Lyu, Jian Tao, Xiu Li, Furong Huang, Huazhe Xu (* equal contribution)
Under review. 2024
Inspired by human cognition, we propose a new multi-modal model-based RL approach named Dreaming with Large Language Models (DLLM).