avatar

Yuhan Rui

Undergraduate Student
Incoming Ph.D. Student
SJTU & ZGCA
A climber scaling the AGI mountain.
Southern University of Science and Technology
Email: ruiyuhan0110@gmail.com
Tel: +86 18915056955

About Me

I am an undergraduate student majoring in Computer Science and Technology at Southern University of Science and Technology, expected to graduate in June 2027. I am also an incoming Ph.D. student in the joint training program between the School of Artificial Intelligence at Shanghai Jiao Tong University (SJTU) and Zhongguancun Academy (ZGCA), starting in September 2027 and advised by Assistant Professor Qibing Ren.

At SUSTech, I am advised by Prof. Qi Hao and Research Assistant Professor Meiying Zhang. I was also a research intern at Prof. Shanghang Zhang’s HMI Lab, Peking University, and I am an early intern at Muka Robotics, where Dr. Xiaowei Chi has been a deeply important mentor and a generous guide who helped lead me into embodied AI.

My interests grow from a simple question: how can machines perceive dynamic scenes, reason across language and vision, and act safely in the physical world? I work around autonomous driving, computer vision, multimodal learning, NLP, world models, and embodied AI, with a particular focus on video-text retrieval, dangerous scene detection, and object detection.

I see AGI as a mountain: perception draws the map, language ties the rope, and action makes the climb real. I am still early in the ascent, but I am moving upward with curiosity, discipline, and a willingness to build.

Research Interests

  • Autonomous Driving: video-text retrieval, dangerous scene detection, safety-critical scene understanding
  • Computer Vision: object detection, visual representation learning
  • Multimodal Learning & NLP: vision-language understanding, context engineering
  • Safe Reinforcement Learning: constrained policy optimization, tail-risk-aware decision making
  • World Models & Embodied AI: latent world models, laboratory embodied benchmarks, compositional generalization

Experience

  1. Shanghai Jiao Tong University
  2. Zhongguancun Academy (ZGCA)
  3. Southern University of Science and Technology
    • (2023.09-2027.06) B.Eng. in Computer Science and Technology
  4. SUSTech iSUS Lab
  5. HMI Lab, National Key Laboratory for Multimedia Information Processing
  6. Muka Robotics
    • (2026.04-Present) Early-stage intern contributing as one of the company's initial team members, mentored by Dr. Xiaowei Chi

News🔥

Selected Publications

  1. PermVLA: Factorization Order as a Regularizer for VLA Learning teaser arXiv
    PermVLA: Factorization Order as a Regularizer for VLA Learning
    Yanqiao Chen*, Yuhan Rui*, Dongsheng Hou*, Zijie Nie, Yutong Wan, Qi Hao * Equal contribution
    arXiv preprint, 2026
    PDF arXiv

  2. Token-World: World Modeling in Vision-Language Model Token Space for Robot Manipulation teaser arXiv
    Token-World: World Modeling in Vision-Language Model Token Space for Robot Manipulation
    Chuyao Fu*, Xiaowei Chi*, Yuhan Rui, ..., Shanghang Zhang * Equal contribution
    arXiv preprint, 2026
    PDF arXiv Project Page

  3. BCPPO: Bachelier-Inspired Constrained Proximal Policy Optimization for Tail-Risk-Aware Safe Reinforcement Learning teaser arXiv
    BCPPO: Bachelier-Inspired Constrained Proximal Policy Optimization for Tail-Risk-Aware Safe Reinforcement Learning
    Dongsheng Hou*, Yanqiao Chen*, Yuhan Rui* * Equal contribution
    arXiv preprint, 2026
    PDF arXiv

  4. Shapley Context Pruning: A Cooperative Game Perspective for Context Reranking and Pruning teaser arXiv
    Shapley Context Pruning: A Cooperative Game Perspective for Context Reranking and Pruning
    Yanqiao Chen*, Dongsheng Hou*, Yuhan Rui*, Zhen Cao, Yepang Liu * Equal contribution
    arXiv preprint, 2026
    PDF arXiv

  5. From Spatial to Spectral: An Efficient, Frequency-Guided Feature Representation Learner for Small Object Detection teaser arXiv
    From Spatial to Spectral: An Efficient, Frequency-Guided Feature Representation Learner for Small Object Detection
    Yuhan Rui*, Shihan Qiao*, Yibin Lou*, Mingxi Yu*, Yutong Wan, Yanqiao Chen, Dongsheng Hou, Zhen Cao, Athena Zhuoming Zhong, Qi Hao * Equal contribution
    arXiv preprint, 2026
    PDF arXiv

  6. LABSHIELD: A Multimodal Benchmark for Safety-Critical Reasoning and Planning in Scientific Laboratories teaser arXiv
    LABSHIELD: A Multimodal Benchmark for Safety-Critical Reasoning and Planning in Scientific Laboratories
    Qianpu Sun, Xiaowei Chi, Yuhan Rui, Ying Li, Kuangzhi Ge, Jiajun Li, Sirui Han, Shanghang Zhang
    arXiv preprint, 2026
    PDF arXiv

  7. OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining teaser arXiv
    OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining
    Yuran Wang*, Siqiao Huang*, Mingleyang Li*, Chenhao Zhang*, Jiaqi Liang*, ..., Yuhan Rui, ..., Lin Shao, Hang Zhao * Equal contribution
    arXiv preprint, 2026
    PDF arXiv Code Project Page

Miscellaneous

  • 🎓 I served as a peer mentor for Class 2404 at Zhixin College, SUSTech, helping first-year students settle into university life and staying close enough to become both a guide and a friend.
  • 🎻 I have a solid command of the violin, but if I am honest, rock music probably runs louder in my blood; I want to pick up the 🎸 electric guitar or bass and start a rock band someday.
  • 💿 I am a devoted music lover and currently collecting vinyl records vinyl record. Prince and David Bowie are my personal GOATs; Sheena Ringo, Björk, and Hikaru Utada hold the same place for me. I am always up for music conversations, and I may share some playlists here when time allows.
  • 🏃 I am trying to build a serious fitness habit. I used to run regularly, before research deadlines turned me into a temporary couch potato.
  • 🧸 I have a soft spot for Brown bears: three identical Brown bear pillows live with me in Changzhou, Shenzhen, and Beijing.