Yuxuan Cai is a researcher in Foundation Model Group, Megvii Technology, Beijing, China. He graduated from Northeastern University in 2021 with a master degree in Computer Engineering, supervised by Professor Yanzhi Wang. His work has been published in some high-impact conferences (AAAI, NIPS).
His research interests include:
- Network Architecture Design
- Foundation Models
- Self Supervised Learning
- Model Compression
Useful links:
- Google Scholar: Google Scholar
- dblp: dblp
- LinkedIn: LinkedIn
Contact Me
- E-mail: nightsnackc@gmail.com
- Github: https://www.github.com/nightsnack/
Publications
Arxiv
- Yuxuan Cai, Yizhuang Zhou, Qi Han, Jianjian Sun, Xiangwen Kong, Jun Li, Xiangyu Zhang, "Reversible Column Networks".
Conference publications
Yuxuan Cai, Hongjia Li, Geng Yuan, Wei Niu, Yanyu Li, Xulong Tang, Bin Ren, and Yanzhi Wang, “YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design“, to appear in AAAI, 2021. (Acceptance Rate: 20.9%)
Geng Yuan, Payman Behnam, Yuxuan Cai, Ali Shafiee, Jingyan Fu, Zhiheng Liao, Zhengang Li, Xiaolong Ma, Jieren Deng, Jinhui Wang, Mahdi Bojnordi, Yanzhi Wang, and Caiwen Ding, "TinyADC: Peripheral Circuit-aware Weight Pruning Framework for Mixed-signal DNN Accelerators," 27'th Annual Design, Automation, and Test in Europe Conference (DATE), 2021
Zhengang Li, Geng Yuan, Wei Niu, Pu Zhao, Yanyu Li, Yuxuan Cai, Yanzhi Wang, “NPAS: A Compiler-aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration”, to appear in CVPR, 2021
Yuxuan Cai, Geng Yuan, Hongjia Li, Wei Niu, Yanyu Li, Xulong Tang, Bin Ren, and Yanzhi Wang, “A Compression-Compilation Co-Design Framework Towards Real-Time Object Detection on Mobile Devices”, to appear in AAAI, 2021 (Demonstration Paper).
Hongjia Li, Geng Yuan, Wei Niu, Yuxuan Cai, Mengshu Sun, Bin Ren, Xue Lin, and Yanzhi Wang, “Real-Time Mobile Acceleration of DNNs: From Computer Vision to Medical Applications”, in ASP-DAC, 2021
Yuxuan Cai, Geng Yuan, Hongjia Li, Wei Niu, Yanyu Li, Xulong Tang, Bin Ren, and Yanzhi Wang, “YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design”, in NeurIPS 2020 Workshop on Machine Learning for Autonomous Driving.