MENU

About Me

Hi, I am Yuqi Xie, you can also call me Leo. I am a Computer Science MS student studying at UT Austin. I obtained my Bachelor's degree in ECE from Shanghai Jiaotong University (SJTU) and Bachelor's degree in CS from Umich.

I'm interested in embodied agents and Large Language Models. I previously worked with Dr. Jim Fan from the NVIDIA research team. We published Voyager together. Now, I'm working in RPL lab advised by Prof. Yuke Zhu.

Education

Aug 2023 - Present
M.S. in Computer Science
University of Texas at Austin
Sep 2021 - May 2023
B.S.E. in Computer Science
University of Michigan
Sep 2019 - Jun 2021
B.S.E. in Electrical and Computer Engineering
Joint Institute at Shanghai Jiaotong University

Interests

  • Foundation Models

  • General-purpose Agents

  • Multimodal Learning

  • Robotics

  • Reinforcement Learning

    • Awards & Scholarships

    Roger King Scholarship
    Aug 2022
    SJTU Undergraduate Excellent Scholarship
    Nov 2020

    Selected Project

    Voyager: An Open-Ended Embodied Agent with Large Language Models
    May 1st, 2023
    #python

    We introduce Voyager, the first LLM-powered embodied lifelong learning agent in Minecraft that continuously explores the world, acquires diverse skills, and makes novel discoveries without human intervention. Voyager consists of three key components: 1) an automatic curriculum that maximizes exploration, 2) an ever-growing skill library of executable code for storing and retrieving complex behaviors, and 3) a new iterative prompting mechanism that incorporates environment feedback, execution err ...

    MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
    Apr 1st, 2021
    #python

    Autonomous agents have made great strides in specialist domains like Atari games and Go. However, they typically learn tabula rasa in isolated environments with limited and manually conceived objectives, thus failing to generalize across a wide spectrum of tasks and capabilities. Inspired by how humans continually learn and adapt in the open world, we advocate a trinity of ingredients for building generalist agents: 1) an environment that supports a multitude of tasks and goals, 2) a large-scale ...