Tsinghua Univerisity Laboratory of Brain and Intelligence
Beijing, China (On-site) | May 2024 - Present
Research Asistant
- AToM-Bot: Embodied Fulfillment of Unspoken Human Needs with Affective Theory of Mind (detail in project section)
- TBD
About me
I am a third-year student at UC Berkeley, pursuing a dual major in Computer Science and Applied Mathematics, with a strong passion for the AI industry and AI research. My academic journey is complemented by hands-on experience as a research assistant at Tsinghua University, where I focused on AI agents. This role honed my skills in developing and understanding advanced AI technologies. I am dedicated to exploring the transformative potential of AI agents and eager to contribute to the field through innovative research and practical applications.
Education
University of California, Berkeley
2022-2026
Computer Science & Applied Mathematics
Relevant Courses
CS
: Data Structures, Computer Architecture, Efficient Algorithms and Intractable Problems, Introduction to Artificial Intelligence, Large Language Model Agents
Math
: Multivariable Calculus, Discrete Math, Linear Algebra, Abstract Linear Algebra, Real Analysis
Skills
Programming Languages
- Python
- Java
- C
Robotics
ROS: Robotic Operating System
Machine Learning
TBD: TBD
Databases
TBD: TBD
DevOps
TBD: TBD
Collaboration Tools
Version Control: Git, Github
Developer Tools
- Git/GitHub
Languages
- Chinese (Native)
- English (Bilingual proficiency)
UC Berkeley Upsilon Pi Epsilon Computer Science Honor Society
Berkeley, California, USA | February 2024 - Present
Student Member
AToM-Bot: Embodied Fulfillment of Unspoken Human Needs with Affective Theory of Mind
April 2024 - June 2024
Research Asistant
- We propose AToM-Bot, a novel task generation and execution framework for proactive robot-human interaction, which leverages the human mental and physical state inference capabilities of the Vision Language Model (VLM) prompted by the Affective Theory of Mind (AToM). Without requiring explicit commands by humans, AToM-Bot proactively generates and follows feasible tasks to improve general human well-being.
- When around humans, AToM-Bot first detects current human needs based on inferred human states and observations of the surrounding environment. It then generates tasks to fulfill these needs, taking into account its embodied constraints. We designed 16 daily life scenarios spanning 4 common scenes and tasked the same visual stimulus to 59 human subjects and our robot. We used the similarity between human open-ended answers and robot output, and the human satisfaction scores to metric robot performance. AToM-Bot received high human evaluations in need detection (6.42/7, 91.7%), embodied solution (6.15/7, 87.8%) and task execution (6.17/7, 88.1%). We show that AToM-Bot excels in generating and executing feasible plans to fulfill unspoken human needs. Videos and code are available at https://affective-tom-bot.github.io/.
