avatar

Zixuan Wang

Undergraduate Student
Tsinghua University
wang-zx23@mails.tsinghua.edu.cn


About Me

I am Zixuan Wang, a third-year undergraduate student (admitted in 2023) majoring in Mathematical and Physical Basic Science (Department of Physics) with a minor in Artificial Intelligence at Tsinghua University. In Fall 2025, I was an exchange student at UC San Diego. I have worked as a research intern at MiroMind AI (Shanda Group), supervised by Dr. Yuntao Chen. Currently, I am conducting remote research at UCSD MixLab, supervised by Dr. Zhen Wang.

Beyond academics and research... 🌍 Exploration: I enjoy traveling and experiencing diverse cultures. I spent an unforgettable Christmas 🎄 in 2025 by the seaside in the beautiful town of La Jolla 🏡.
🔬 Visits: In Summer 2024, I participated in a social practice program in Singapore 🇸🇬, conducting research visits to leading institutions including A*STAR, Nanyang Technological University 🎓, and National University of Singapore 🏛️.
🤖 Competition: In Summer 2025, I contributed as a team member to the Tinker Robot Team at Tsinghua University's Future Robotics Club, competing in RoboCup@Home 2025 in Salvador, Brazil 🇧🇷. We developed an LLM-driven domestic service robot with decision-making capabilities, achieving 8th place globally 🏆.
🎼 Music: I am an active member of the Tsinghua University Symphonic Band, playing saxophone 🎷 and contributing to performances 🎭 and campus events 🎪.
🧗 Sports: I enjoy volleyball🏐, swimming🏊, and gyms 🏋️!

Research Interests

My research interests lie in advancing LLM algorithms that enable more reliable, adaptive, and autonomous interaction with humans. I am particularly interested in LLM alignment, leveraging synthetic data, structured supervision, and preference-based training to improve models’ understanding of human intent while ensuring privacy and safety. I also work on agentic LLM systems with long-horizon capabilities, including long-context reasoning, planning, tool use, and self-refinement in real-world grounded environments.

Education

Publications

  1. Submission
    S³-Sim: Simulating Humans for Personalized Language Modeling
    Jinzhou Tang*, Yufan Zhou*, Zixuan Wang*, Zhaoxiang Feng, Xinle Yu, Steven Ngo, Zhengding Hu, Luoshang Pan, Lianhui Qin, Yufei Ding, Tianmin Shu, Jingbo Shang, Zhiting Hu, Zhen Wang†
    In Submission
    (*Equal Contribution)

  2. Submission
    Lightweight Neural Refinement for Drift Calibration in Eye Tracking Systems
    Liu Jiaqi*, Zixuan Wang*, Yuhong Zhang, Dingkang Liang, Jane Hanqi Li, Tzyy-Ping Jung, Gert Cauwenberghs†
    In Submission
    (*Equal Contribution)

Technical Reports

  1. Preprint
    MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents
    Preprint, arXiv:2511.11793
    Code Project Page Project Contributor

Course Projects

  1. Course
    Ego-embodied Reasoner: Egocentric Embodied Reasoning and Planning with MLLM via Reinforcement Learning
    Deep Reinforcement Learning Course Project, Instructed by Professor Huazhe Xu
    PDF Code Video Project Leader

  2. Course
    EgoHOI: Prior-Guided 3D Hand-Object Interaction Reconstruction from Monocular Egocentric RGB Video
    Computer Vision Course Project
    PDF Code Project Leader

  3. Course
    Unconditional and Image-conditioned 3D Generation
    3D Visual Computing Course Project, instructed by Professor Li Yi
    PDF Code Video Independent

  4. Course
    Human Skeleton and Skin Generation
    Fundamentals of Computer Graphics Course Project, the 5-th Jittor AI competition, track 2
    PDF Code Project Leader

  5. Course
    Project Reading Report
    Object Oriented Programming Course Project
    PDF Code Independent


Powered by Jekyll and Minimal Light theme.