关于我
2025 年，我联合创办了一家 AI 公司，专注于超大规模视频 AI 的基础设施建设；
A 轮融资估值 13.2 亿美金。
此前，我在自动驾驶头部公司
Momenta（HKEX: 6880）任高级研发总监，负责训练与推理基础设施 ——
搭建把感知、规划模型从研究原型送上量产车、并适配多种车载芯片的一整套系统。
在 Momenta 之前，我在商汤科技（HKEX: 0020）担任研究副总监，
导师为
王晓刚教授和闫俊杰博士。我领导 Model-ToolChain 团队，构建商汤内部的 AI 平台 ——
一套共享的训练、压缩、部署栈，支撑了公司大部分智慧城市与智能车业务，
模型产量以约每年 2 倍的速度增长。
团队的部分工作以
ModelTC
组织在 GitHub 开源，相关技术文章发表于知乎专栏
《踢翻炼丹炉》。
我最早以全职实习生的身份加入商汤，在视频智能组随
闫俊杰博士实习两年，负责高性能视频分析系统（人脸、车辆、行人）及算法向嵌入式平台的移植；
期间带队拿下 ECCV MOT16 多目标跟踪挑战赛第一名。
求学期间，我带领北航 HPC 团队获 ASC 2015
学生超算竞赛一等奖，并在微软北京 IoT 团队实习半年，参与 IoT
通信协议开发。
我在 2015 年和 2018 年先后拿到北航计算机科学本科和硕士学位。
硕士期间师从史晓华教授，做过三个独立方向的研究：JVM 内存 profiling；
CompCert（形式化验证编译器）；把大规模深度学习语言模型用于文本查错纠错。
高中开始学习信息学竞赛，连续两年 NOIp 一等奖（全国第 55 名），
保送北航计算机学院。
论文
2024
Towards Frame Rate Agnostic Multi-Object Tracking
[PDF]
IJCV 2024
Weitao Feng, Lei Bai, Yongqiang Yao, Fengwei Yu,
Wanli Ouyang
2023
UniHCP: A Unified Model for Human-Centric Perceptions
[PDF]
CVPR 2023
Yuanzheng Ci, Yizhou Wang, Meilin Chen, Shixiang Tang, Lei Bai, Feng
Zhu, Rui Zhao, Fengwei Yu, Donglian Qi, Wanli
Ouyang
The Equalization Losses: Gradient-Driven Training for Long-tailed
Object Recognition
[PDF]
TPAMI 2023
Jingru Tan, Bo Li, Xin Lu, Yongqiang Yao,
Fengwei Yu, Tong He, Wanli Ouyang
Exploiting Subgraph Similarities for Efficient Auto-tuning of Tensor
Programs
ICPP 2023
Mingzhen Li, Hailong Yang, Shanjun Zhang,
Fengwei Yu, Ruihao Gong, Yi Liu, Zhongzhi Luan,
Depei Qian
SysNoise: Exploring and Benchmarking Training-Deployment System
Inconsistency
MLSys 2023
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]
IPDPS 2023
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
2022
Outlier Suppression: Pushing the Limit of Low-bit Transformer
Language Models
[PDF]
NeurIPS 2022
Xiuying Wei, Yunchen Zhang, Xiangguo Zhang, Ruihao Gong, Shanghang
Zhang, Qi Zhang, Fengwei Yu, Xianglong Liu
Equalized Focal Loss for Dense Long-Tailed Object Detection
[PDF]
CVPR 2022
Bo Li, Yongqiang Yao, Jingru Tan, Gang Zhang,
Fengwei Yu, Jianwei Lu, Ye Luo
NNLQP: A Multi-Platform Neural Network Latency Query and Prediction
System with an Evolving Database
ICPP 2022
Liang Liu, Mingzhu Shen, Ruihao Gong, Fengwei Yu,
Hailong Yang
QDrop: Randomly Dropping Quantization for Extremely Low-bit
Post-Training Quantization
[PDF]
ICLR 2022
Xiuying Wei, Ruihao Gong, Yuhang Li, Xianglong Liu,
Fengwei Yu
Supervision Exists Everywhere: A Data Efficient Contrastive
Language-Image Pre-training Paradigm
[PDF]
ICLR 2022
Yangguang Li, Feng Liang, Lichen Zhao, Yufeng Cui, Wanli Ouyang,
Jing Shao, Fengwei Yu, Junjie Yan
2021
Once Quantization-Aware Training: High Performance Extremely Low-Bit
Architecture Search
[PDF]
ICCV 2021
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]
ICCV 2021
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]
ICCV 2021
Yuhang Li, Feng Zhu, Ruihao Gong, Mingzhu Shen, Xin Dong,
Fengwei Yu, Shaoqing Lu, Shi Gu
Incorporating Convolution Designs into Visual Transformers
[PDF]
ICCV 2021
Kun Yuan, Shaopeng Guo, Ziwei Liu, Aojun Zhou,
Fengwei Yu, Wei Wu
MQBench: Towards Reproducible and Deployable Model Quantization
Benchmark
[PDF]
NeurIPS 2021
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]
CVPR 2021
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]
ICLR 2021
Yuhang Li, Ruihao Gong, Xu Tan, Yang Yang, Peng Hu, Qi Zhang,
Fengwei Yu, Wei Wang, Shi Gu
2020
Extremely Low-bit Convolution Optimization for Quantized Neural
Network on Modern Computer Architectures
[PDF]
ICPP 2020
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]
ICLR 2020 NAS Workshop
Yuhang Li, Ruihao Gong, Fengwei Yu, Xin Dong,
Xianglong Liu
Towards Unified INT8 Training for Convolutional Neural Networks
[PDF]
CVPR 2020
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]
CVPR 2020
Haotong Qin, Ruihao Gong, Xianglong Liu, Mingzhu Shen, Ziran Wei,
Fengwei Yu, Jingkuan Song
2019
Differentiable Soft Quantization: Bridging Full-Precision and
Low-Bit Neural Networks
[PDF]
ICCV 2019
Ruihao Gong, Xianglong Liu, Shenghu Jiang, Tianxiang Li, Peng Hu,
Jiazhen Lin, Fengwei Yu, Junjie Yan
2016
POI: Multiple Object Tracking with High Performance Detection and
Appearance Feature
[PDF]
ECCV 2016 Workshop
Fengwei Yu, Wenbo Li, Quanquan Li, Yu Liu, Xiaohua
Shi, Junjie Yan
