Forwil's home page

Profile Image
Fengwei Yu(Forwil) R&D Architect Momenta forwil@foxmail.com Github / Google scholar / CV

Research

I'm diving in deep learning industrialization. Here is the areas I am interested in


News

About me / bio

I am now holding a position of Senior R&D Director at Momenta, an industry leader in autonomous driving technology. I lead a AI-Infra team that specializes in training accelerators、model quantization and deep learning compiler.


Prior to this, I was a Vice Research Director and team leader of a AI-Infra team called Model-ToolChain of Sensetime Research under the supervisor of Prof. Wang-Xiaogang and Dr. Yan-Junjie, working on deep learning system.

You can find our opensource project in Github ModelTC group. And find tech blog on Zhihu 踢翻炼丹炉


I enjoy 2-years full-time internship in Sensetime Research Video Intelligent Group under the supervisor of Dr. Yan-Junjie on developing high-performance video face/vehicle/pedestrian analysis system and porting algorithm into embedded system.


Before join sensetime, I leaded BUAA HPC team get first-prize on ASC Student Supercomputer Challenge 2015 and spend half an year intership on Microsoft IOT team Beijing to develop IoT communication protocal.


I earned my Master's and Bachelor's degrees in Computer Science from Beihang University in 2018 and 2015, respectively, under the guidance of Professor Xiaohua Shi. My studies centered on JVM memory profiling, the CompCert project, and language models.

Publications

Exploiting Subgraph Similarities for Efficient Auto-tuning of Tensor Programs PDF
2023 International Conference on Parallel Processing（ICPP）
Mingzhen Li, Hailong Yang, Shanjun Zhang, Fengwei Yu, Ruihao Gong, Yi Liu, Zhongzhi Luan, Depei Qian
SysNoise: Exploring and Benchmarking Training-Deployment System Inconsistency PDF
2023 Conference on Machine Learning and Systems（MlSys）
Yan Wang, Yuhang Li, Ruihao Gong, Aishan Liu, Yanfei Wang, Jian Hu, Yongqiang Yao, Yunchen Zhang, Tianzi Xiao,Fengwei Yu, Xianglong Liu
Exploiting Input Tensor Dynamics in Activation Checkpointing for Efficient Training on GPU PDF
2023 International Parallel & Distributed Processing Symposium（IPDPS）
Jianjin Liao, Mingzhen Li, Hailong Yang, Qingxiao Sun, Biao Sun, Jiwei Hao, Tianyu Feng, Fengwei Yu, Shengdong Chen, Ye Tao, Zicheng Zhang, Zhongzhi Luan, Depei Qian
NNLQP: A Multi-Platform Neural Network Latency Query and Prediction System with An Evolving Database PDF
2022 International Conference on Parallel Processing（ICPP）
Liang Liu, Mingzhu Shen, Ruihao Gong, Fengwei Yu, Hailong Yang
QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization PDF
2022 International Conference on Learning Representations（ICLR）
Xiuying Wei, Ruihao Gong, Yuhang Li, Xianglong Liu, Fengwei Yu
Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm PDF
2022 International Conference on Learning Representations（ICLR）
Yangguang Li, Feng Liang, Lichen Zhao, Yufeng Cui, Wanli Ouyang, Jing Shao, Fengwei Yu, Junjie Yan
Once Quantization-Aware Training: High Performance Extremely Low-Bit Architecture Search PDF
2021 International Conference on Computer Vision（ICCV）
Mingzhu Shen, Feng Liang, Ruihao Gong, Yuhang Li, Chuming Li, Chen Lin, Fengwei Yu, Junjie Yan, Wanli Ouyang
Differentiable Dynamic Wirings for Neural Networks PDF
2021 International Conference on Computer Vision（ICCV）
Kun Yuan, Quanquan Li, Shaopeng Guo, Dapeng Chen, Aojun Zhou, Fengwei Yu, Ziwei Liu
MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing PDF
2021 International Conference on Computer Vision（ICCV）
Yuhang Li, Feng Zhu, Ruihao Gong, Mingzhu Shen, Xin Dong, Fengwei Yu, Shaoqing Lu, Shi Gu
Incorporating convolution designs into visual transformers PDF
2021 International Conference on Computer Vision（ICCV）
Kun Yuan, Shaopeng Guo, Ziwei Liu, Aojun Zhou, Fengwei Yu, Wei Wu
MQBench: Towards Reproducible and Deployable Model Quantization Benchmark PDF
2021 Conference on Neural Information Processing Systems (NeurIPS）
Yuhang Li, Mingzhu Shen, Jian Ma, Yan Ren, Mingxin Zhao, Qi Zhang, Ruihao Gong, Fengwei Yu, Junjie Yan
Diversifying Sample Generation for Accurate Data-Free Quantization PDF
2021 Conference on Computer Vision and Pattern Recognition（CVPR）
Xiangguo Zhang, Haotong Qin, Yifu Ding, Ruihao Gong, Qinghua Yan, Renshuai Tao, Yuhang Li, Fengwei Yu, Xianglong Liu
BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction PDF
2021 International Conference on Learning Representations（ICLR）
Yuhang Li, Ruihao Gong, Xu Tan, Yang Yang, Peng Hu, Qi Zhang, Fengwei Yu, Wei Wang, Shi Gu
Extremely Low-bit Convolution Optimization for Quantized Neural Network on Modern Computer Architectures PDF
2020 International Conference on Parallel Processing (ICPP)
Qingchang Han, Yongmin Hu, Fengwei Yu, Hailong Yang, Bing Liu, Peng Hu, Ruihao Gong, Yanfei Wang, Rui Wang, Zhongzhi Luan, Depei Qian
DMS: Differentiable Dimension Search for Binary Neural Networks PDF
2020 International Conference on Learning Representations (ICLR) NAS workshop
Yuhang Li, Ruihao Gong, Fengwei Yu, Xin Dong, Xianglong Liu
Towards Unified INT8 Training for Convolutional Neural Network PDF
2020 Conference on Computer Vision and Pattern Recognition (CVPR)
Feng Zhu, Ruihao Gong, Fengwei Yu, Xianglong Liu, Yanfei Wang, Zhelong Li, Xiuqi Yang, Junjie Yan
Forward and Backward Information Retention for Accurate Binary Neural Networks PDF
2020 Conference on Computer Vision and Pattern Recognition (CVPR)
Haotong Qin, Ruihao Gong, Xianglong Liu, Mingzhu Shen, Ziran Wei, Fengwei Yu, Jingkuan Song
Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks PDF
2019 International Conference in Computer Vision (ICCV)
Ruihao Gong, Xianglong Liu, Shenghu Jiang, Tianxiang Li, Peng Hu, Jiazhen Lin, Fengwei Yu, Junjie Yan.
POI: Multiple Object Tracking with High Performance Detection and Appearance Feature PDF
2016 European Conference on Computer Vision (ECCV) workshop
Fengwei Yu, Wenbo Li, Quanquan Li, Yu Liu, Xiaohua Shi, Junjie Yan

I like this website