About
Now I have moved to Shanghai Academy of Artificial Intelligence for Science (SAIS). And my current research focuses on AI for Science, including multimodal learning and physics informed generative models. We now have several internship positions, please email me if you are interested. xiuyu.sxy [at] gmail [dot] com
My name is SUN Xiuyu and I am the head of the tinyml team at the Machine Intelligence Lab, Alibaba Group. My research now focuses on efficient deep learning computing in computer vision. In the early time of my Alibaba experience, I designed the first generation of deep learning based ranking and recommendation algorithms for Taobao, Tmall and Youku. Also, I was one of the early members of the PAILITAO team, developing visual image search engine for e-commerce.
Research Interests
AI for Science / Multimodal Learning / Physics Informed Generative Models
TinyML / Efficient Neural Network / Model Compression / NAS / AutoML
Computer Vision / Recognition / Object Detection / Retrieval / Compression
Experiences
Senior Researcher Shanghai Academy of Artificial Intelligence for Science 2023-Present
Staff Algorithm Engineer DAMO Academy, Alibaba Group 2018 – 2023
Algorithm Engineer Alibaba Group 2014 – 2018
Algorithm Engineer NEC Labs China 2012 – 2014
Research Assistant SIAT, Chinese Academy of Sciences 2011 – 2012
TinyML Project
Neural Architecture Search
PreNAS: Preferred One-Shot Learning Towards Efficient Vision Transformer Search, ICML 2023, [pdf][code]
Haibin Wang, Ce Ge, Hesen Chen, Xiuyu Sun*(corresponding author)
DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network, CVPR 2023 , [pdf][code]
Xuan Shen, Yaohua Wang, Ming Lin, Dylan Huang, Hao Tang, Xiuyu Sun*(corresponding author) , Yanzhi Wang
Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition, ICLR 2023 [pdf][code]
Junyan Wang, Zhenhong Sun, Yichen Qian, Dong Gong, Xiuyu Sun*(corresponding author) , Ming Lin, Maurice Pagnucco, Yang Song
Entropy-Driven Mixed-Precision Quantization for Deep Network Design on IoT Devices, NeurIPS 2022 [ pdf] [slides][code]
Zhenhong Sun, Ce Ge, Junyan Wang, Ming Lin, Hesen Chen, Hao Li, Xiuyu Sun*(corresponding author)
MAE-DET: Revisiting Maximal Entropy Principle in Zero-Shot NAS for Efficient Object Detection, ICML 2022 [pdf] [code]
Zhenhong Sun, Ming Lin, Zhiyu Tan, Xiuyu Sun*(corresponding author) , Hao Li, Rong Jin
Zen-NAS: A Zero-Shot NAS for High-Performance Image Recognition, ICCV 2021 [pdf][code]
Ming Lin, Pichao Wang, Zhenhong Sun, Hesen Chen, Xiuyu Sun, Qi Qian, Hao Li, Rong Jin
Neural architecture design for gpu-efficient networks, Pre-print 2020 [pdf]
Ming Lin, Hesen Chen, Xiuyu Sun, Qi Qian, Hao Li, Rong Jin
Efficient Vision Applications
DAMO-YOLO: A Report on Real-Time Object Detection Design, Arxiv 2022 [pdf][code]
Xianzhe Xu, Yiqi Jiang, Weihua Chen, Yilun Huang, Yuan Zhang, Xiuyu Sun*(corresponding author)
GiraffeDet: A Heavy-Neck Paradigm for Object Detection, ICLR 2022 [pdf][code]
Yiqi Jiang, Zhiyu Tan, Junyan Wang, Xiuyu Sun*(corresponding author) , Ming Lin, Hao Li
MuffNet: Multi-Layer Feature Federation for Mobile Deep Learning , ICCVW 2019 [pdf]
Hesen Chen, Ming Lin, Xiuyu Sun*(corresponding author), Qian Qi, Hao Li, Rong Jin
Efficient Training
Beyond Visual Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks, CVPR 2023 , [pdf][code]
Weihua Chen, Xianzhe Xu, Jian Jia, Hao Luo, Yaohua Wang, Fan Wang, Rong Jin, Xiuyu Sun*(corresponding author)
Robust Graph Structure Learning over Images via Multiple Statistical Tests, NeurIPS 2022 [ pdf ]
Yaohua Wang, Fangyi Zhang, Ming Lin, Senzhang Wang, Xiuyu Sun*(corresponding author) , Rong Jin
Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Space, ICLR 2022 [pdf][code]
Yaohua Wang, Yaobin Zhang, Fangyi Zhang, Senzhang Wang, Ming Lin, YuQi Zhang, Xiuyu Sun*(corresponding author) ,
Exploring the Quality of GAN Generated Images for Person Re-Identification, ACMMM 2021 [pdf]
Yiqi Jiang, Weihua Chen, Xiuyu Sun*(corresponding author) , Xiaoyu Shi, Fan Wang, Hao Li
Fine-Grained AutoAugmentation for Multi-Label Classification, Pre-print 2021 [pdf]
Ya Wang, Hesen Chen, Fangyi Zhang, Yaohua Wang, Xiuyu Sun*(corresponding author) , Ming Lin, Hao Li
Learning to Cluster Faces via Transformer, Pre-print 2021 [pdf]
Jinxing Ye, Xioajiang Peng, Baigui Sun, Kai Wang, Xiuyu Sun, Hao Li, Hanqing Wu
Learned Compression
JMPNET: Joint Motion Prediction For Learning-Based Video Compression, ICASSP 2022
Dongyang Li, Zhenhong Sun, Zhiyu Tan, Xiuyu Sun, Fangyi Zhang, Yichen Qian, Hao Li
Entroformer: A Transformer-based Entropy Model for Learned Image Compression, ICLR 2022 [pdf][code]
Yichen Qian, Ming Lin, Xiuyu Sun*(corresponding author) , Zhiyu Tan, Rong Jin
Interpolation Variable Rate Image Compression, ACMMM 2021 [code]
Zhenhong Sun, Zhiyu Tan, Xiuyu Sun*(corresponding author) , Fangyi Zhang, Yichen Qian, Dongyang Li, Hao Li
Learning Accurate Entropy Model With Global Reference For Image Compression, ICLR 2021 [pdf][code]
Yichen Qian, Zhiyu Tan, Xiuyu Sun*(corresponding author) , Ming Lin, Dongyang Li, Zhenhong Sun, Hao Li, Rong Jin