Rui Hong

PhD Student, George Mason University

I am a Ph.D. student in Computer Science at George Mason University, advised by Prof. Jana Košecká. My research focuses on sign language production and translation, 3D pose estimation, video generation, multimodal AI, and generative models.

Prior to GMU, I received my M.S. from Huazhong University of Science and Technology (HUST). I then worked as an AI/CV Algorithm Engineer at Zhejiang Dahua Technology and OPPO. Most recently, I was an Algorithm Engineer at IDEA Research, founded by Prof. Harry Shum, where I was mentored by Prof. Lei Zhang.

selected publications

  1. Conditional Collapse in Sign Language Production: A Diagnostic and a Scaling Argument
    Rui Hong and Jana Košecká
    arXiv preprint arXiv:2606.01643, 2026
    Manuscript under review
    arXiv
  2. Gesture-Aware Pretraining and Token Fusion for 3D Hand Pose Estimation
    Rui Hong and Jana Košecká
    arXiv preprint arXiv:2603.17396, 2026
    Accepted to PhysHuman Workshop at CVPR 2026
    arXiv
  3. Toward Phonology-Guided Sign Language Motion Generation: A Diffusion Baseline and Conditioning Analysis
    Rui Hong and Jana Košecká
    arXiv preprint arXiv:2603.17388, 2026
    Accepted to GenSign Workshop at CVPR 2026
    arXiv
  4. Motion-Adaptive Temporal Attention for Lightweight Video Generation with Stable Diffusion
    Rui Hong and Shuxue Quan
    In IS&T Electronic Imaging, 2026
    arXiv
  5. To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs
    Rui Hong and Shuxue Quan
    arXiv preprint arXiv:abs/2603.18373, 2026
    Manuscript under review
    arXiv

Projects

StockLens — A Flask-based stock analysis tool supporting both A-share (Chinese) and US markets. Features AI-powered analysis using DeepSeek and GPT-4o-mini, a watchlist system for tracking favorite stocks, and dedicated AI functions optimized for token efficiency. Built as a personal side project driven by interest in financial markets.