Scholar
Xinyin Ma
Google Scholar ID: jFUKS0oAAAAJ
National University of Singapore
Citations & Impact
Citations
2,446
H-index
15
i10-index
18
Publications
20
Co-authors
14
list available
Publications
Resume (English only)
Academic Achievements
- September 2025: Three papers (dKV-Cache, Thinkless, and VeriThinker) accepted by NeurIPS'25 and one survey accepted by TMLR; August 2025: Started the internship at NVIDIA; February 2025: Co-organized the 2nd workshop on Efficient Large Vision Models, CVPR'25; January 2025: Awarded KAUST Rising Stars 2025; November 2024: Awarded Google PhD Fellowship; December 2023: New work DeepCache accelerates Diffusion Models; June 2023: Released LLM-Pruner, the first structural pruning work of LLM.
Research Experience
- Working as a PhD research intern at NVIDIA Fundamental Generative AI Research (GenAIR) group.
Education
- Obtained master's and bachelor's degrees in computer science from Zhejiang University, advised by Prof. Weiming Lu; currently pursuing a Ph.D. at the National University of Singapore, supervised by Prof. Xinchao Wang.
Background
- Currently a final-year Ph.D. student at xML-Lab, National University of Singapore, under the supervision of Prof. Xinchao Wang. Research interests include efficiency research for generative models, such as large language models, reasoning models, and diffusion language models; image and video diffusion models; data-centric compression techniques, etc.
Miscellany
- Expected to graduate before June 2026 and is currently on the job market.
