Muyang Li
Scholar

Muyang Li

Google Scholar ID: f_sApl4AAAAJ
Massachusetts Institute of Technology
Computer VisionComputer GraphicsSystem
Citations & Impact
All-time
Citations
1,052
 
H-index
10
 
i10-index
10
 
Publications
17
 
Co-authors
29
list available
Resume (English only)
Academic Achievements
  • Publication: 'Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation', NeurIPS 2025.
  • Publication: 'SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models', ICLR 2025 Spotlight.
  • Publication: 'DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models', CVPR 2024 Highlight.
  • Publication: 'Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models', T-PAMI & NeurIPS 2022.
  • Publication: 'GAN Compression: Efficient Architectures for Interactive Conditional GANs', T-PAMI & CVPR 2020.
  • Awards: Best Pitch Award, MARC 2025, Jan 2025; Seneff-Zue CS Fellowship, $98K, Sep 2023; Honorable Mention, 2019 American Interdisciplinary Contest in Modeling (ICM), Jan 2019, etc.
Research Experience
  • Summer Intern at NVIDIA, Santa Clara, working with Prof. Song Han, May 2024 - Aug 2024.
  • Summer Intern at NVIDIA, Shanghai, working with Prof. Song Han and Ming-Yu Liu, Jun 2023 - Aug 2023.
  • Summer Intern at OmniML Inc., San Jose, working with Prof. Song Han, May 2022 - Aug 2022.
  • Data Scientist at Dawnlight Inc., Shanghai, working with Prof. Song Han, Jul 2020 - Jul 2021.
  • Research Assistant at MIT HAN Lab, Cambridge, working with Prof. Jun-Yan Zhu and Prof. Song Han, Jul 2019 - Jan 2020.
Background
  • Research interests: intersection of machine learning, systems, and computer graphics; currently working on building efficient and hardware-friendly generative models with applications in computer vision and graphics.
Miscellany
  • Coach of SJTU's ICPC team, Jun 2019 - Apr 2019; Teaching Assistant for CS147: Data Structure.