Scholar
Weijian Luo
Google Scholar ID: kAYjIR4AAAAJ
Peking University
Citations & Impact
Citations
494
H-index
11
i10-index
13
Publications
20
Co-authors
14
list available
Publications
Resume (English only)
Academic Achievements
- Reviewer for academic journals including Nature Communications (NC), Journal of Machine Learning Research (JMLR), IEEE Transactions on Image Processing (TIP), IEEE Transactions on Neural Networks and Learning Systems (TNNLS), and Pattern Recognition (PR). Also reviews for top AI Conferences such as NeurIPS, ICML, ICLR, CVPR, ICCV, AISTATS, UAI, ACM-MM. Recent publications include 'Ultra-Fast Language Generation via Discrete Diffusion Divergence Instruct' on Arxiv, and two papers accepted by NeurIPS 2025: 'Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation' and 'Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instruction'.
Research Experience
- Senior Research Scientist at Humane Intelligence (hi) lab of Xiaohongshu (RedNote) Inc, Beijing. Leads the research team of large generative understanding models in hi-lab.
Education
- PhD in Statistics and Generative Modeling from Peking University, School of Mathematical Sciences; M.S. in Applied Statistics from Peking University, School of Mathematical Sciences; B.S. in Mathematics from University of Science and Technology of China (USTC).
Background
- Research Interests: Theory and practice for modern one-step text-to-image generative models. Currently leads the research team of large generative understanding foundation models. Professional field: Statistics, Generative Modeling.
Miscellany
- Invited to deliver talks at Google Deepmind Research, 18th X-AGI && China-R Conference, Few-step Diffusion Models meetup, Genmo AI, Biomedical Engineering lab of Peking University, and MAPLE lab of Westlake University.
