I am a 2nd-year Ph.D. student at SMILE lab of Northeastern University (Boston, US), advised by Prof. Yun (Raymond) Fu. Before that, I received my M.S. and B.E. degrees from Zhejiang University (Hangzhou, China) in 06/2019 and 06/2016, respectively, supervised by Prof. Haoji Hu. During 2018 summer, I visited VLLab at University of California, Merced, working with Prof. Ming-Hsuan Yang. I am interested in a variety of topics in computer vision and deep learning, especially deep model compression and interpretation.
- 2020/02: One paper about model compression for ultra-resolution neural style transfer is accepted by CVPR-20. Code released at here.
- 2020/01: I will intern at MERL in the 2020 summer, working with Dr. Michael Jones and Dr. Suhas Lohit.
- 2020/01: 2019 summer intern paper accepted by MLSys-20. (Project: MNN from Alibaba, one of the fastest mobile AI engines on this planet. Welcome trying!)
- 2019/12: One journal paper accepted by IEEE JSTSP.
- 2019/09: Join SMILE lab at NEU to pursue my Ph.D. degree.
- 2019/07: Summer intern at Taobao of Alibaba Group at Hangzhou, China.
- 2019/04: One ICIP-19 paper and ICML-19 workshop paper accepted.
- 2019/03: One IJCNN-19 paper accepted as oral.
| Huan Wang, Yijun Li, Yuehai Wang, Haoji Hu, Ming-Hsuan Yang. "Collabrotive Distillation for Ultra-Resolution Universal Style Transfer". In CVPR-20.|
| Xiaotang Jiang, Huan Wang, Yiliu Chen, Ziqi Wu, et al. "MNN: A Universal and Efficient Inference Engine". In MLSys-20 (Oral).|
| Huan Wang, Xinyi Hu, Qiming Zhang, Yuehai Wang, Lu Yu, Haoji Hu. "Structured Pruning for Efficient ConvNets via Incremental Regularization". In NeurIPS-18 workshop, IJCNN-19 (Oral), journal extension to IEEE JSTSP.|
Paper ( NeurIPS-18 workshop, IJCNN-19, JSTSP)
| Huan Wang*, Qiming Zhang*, Yuehai Wang, Haoji Hu. "Structured Probabilistic Pruning for Convolutional Neural Network Acceleration". In BMVC-18 (Oral).|
- Program committee of ICML-19 workshop
- Reviewer for Neurocomputing, NeurIPS-18 workshop, ICML-19 workshop, IEEE JSTSP, CVPR-20 workshop