Associate Professor, EECS, MIT

Distinguished Scientist, Google DeepMind

kaiming@mit.edu

I am an Associate Professor with tenure in the Department of EECS at MIT. I also work part-time as a Distinguished Scientist at Google DeepMind. My research areas include computer vision and deep learning.

I am best known for my work on Deep Residual Networks (ResNets), which is the most-cited paper of the twenty-first century, according to a Nature article. The proposed residual connections are now being used everywhere in modern deep learning models, including Transformers (e.g., ChatGPT), AlphaGo Zero, AlphaFold, and virtually all GenAI models today, among many others. I am also known for my work on visual perception (e.g., Faster R-CNN, Mask R-CNN) and self-supervised learning (e.g., MoCo, MAE). My publications have over 700,000 citations (as of May 2025).

I am a recipient of several prestigious awards, including the Test of Time Award in NeurIPS 2025, ICCV 2025, the PAMI Young Researcher Award in 2018, the Best Paper Award in ICCV 2017, CVPR 2016, CVPR 2009, the Best Student Paper Award in ICCV 2017, the Best Paper Honorable Mention in CVPR 2021, ECCV 2018, and the Everingham Prize in ICCV 2021.

Before joining MIT in 2024, I was a research scientist at Facebook AI Research (FAIR) from 2016 to 2024, and a researcher at Microsoft Research Asia (MSRA) from 2011 to 2016. I received my PhD degree from the Chinese University of Hong Kong in 2011, and my B.S. degree from Tsinghua University in 2007.



Prospective PhD students: if you are interested in joining my group as a PhD, please submit your application to the EECS admission process (opening Sept.) and tag my name in the system.

Prospective interns and post-docs: if you are interested in joining my group, please email me with your CV and a short research statement.

Back to Basics: Let Denoising Generative Models Denoise
Tianhong Li and Kaiming He
Computer Vision and Pattern Recognition (CVPR), 2026
Tech report, Nov. 2025
arXiv    code

Mean Flows for One-step Generative Modeling
Zhengyang Geng, Mingyang Deng, Xingjian Bai, J. Zico Kolter, and Kaiming He
Conference on Neural Information Processing Systems (NeurIPS), 2025 (Oral)
Tech report, May 2025
arXiv    code

Autoregressive Image Generation without Vector Quantization
Tianhong Li, Yonglong Tian, He Li, Mingyang Deng, and Kaiming He
Conference on Neural Information Processing Systems (NeurIPS), 2024 (Spotlight)
arXiv    code

Masked Autoencoders Are Scalable Vision Learners
Kaiming He*, Xinlei Chen*, Saining Xie, Yanghao Li, Piotr Dollár, and Ross Girshick
Computer Vision and Pattern Recognition (CVPR), 2022 (Oral). Best Paper Nominee
arXiv    code

Exploring Simple Siamese Representation Learning
Xinlei Chen and Kaiming He
Computer Vision and Pattern Recognition (CVPR), 2021 (Oral). Best Paper Honorable Mention
arXiv    code

Momentum Contrast for Unsupervised Visual Representation Learning
Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick
Computer Vision and Pattern Recognition (CVPR), 2020 (Oral). Best Paper Nominee
arXiv    code

Rethinking ImageNet Pre-training
Kaiming He, Ross Girshick, and Piotr Dollár
International Conference on Computer Vision (ICCV), 2019
arXiv

Group Normalization
Yuxin Wu and Kaiming He
European Conference on Computer Vision (ECCV), 2018 (Oral). Best Paper Honorable Mention
International Journal of Computer Vision (IJCV), accepted in 2019
arXiv    code    slides

Non-local Neural Networks
Xiaolong Wang, Ross Girshick, Abhinav Gupta, and Kaiming He
Computer Vision and Pattern Recognition (CVPR), 2018
arXiv    code

Mask R-CNN
Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick
International Conference on Computer Vision (ICCV), 2017 (Oral). ICCV Best Paper Award (Marr Prize)
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), accepted in 2018
arXiv   talk   slides: ICCV tutorial   ICCV oral   COCO workshop   code

Focal Loss for Dense Object Detection
Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár
International Conference on Computer Vision (ICCV), 2017 (Oral). ICCV Best Student Paper Award
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), accepted in 2018
arXiv   code

Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
Priya Goyal, Piotr Dollár, Ross Girshick, Pieter Noordhuis, Lukasz Wesolowski, Aapo Kyrola, Andrew Tulloch, Yangqing Jia, and Kaiming He
Tech report, June 2017
arXiv

Feature Pyramid Networks for Object Detection
Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie
Computer Vision and Pattern Recognition (CVPR), 2017
arXiv   code

Aggregated Residual Transformations for Deep Neural Networks
Saining Xie, Ross Girshick, Piotr Dollár, Zhuowen Tu, and Kaiming He
Computer Vision and Pattern Recognition (CVPR), 2017
arXiv   code

Identity Mappings in Deep Residual Networks
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun
European Conference on Computer Vision (ECCV), 2016 (Spotlight)
arXiv   code

Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun
Computer Vision and Pattern Recognition (CVPR), 2016 (Oral). CVPR Best Paper Award
arXiv   code   talk   slides: ILSVRC workshop  ICML tutorial  CVPR oral

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun
Conference on Neural Information Processing Systems (NeurIPS), 2015. NeurIPS Test of Time Award, 2025
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), accepted in 2016
arXiv   NeurIPS version   code-matlab   code-python

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun
International Conference on Computer Vision (ICCV), 2015. ICCV Test of Time Award (Helmholtz Prize), 2025
arXiv   ICCV version

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun
European Conference on Computer Vision (ECCV), 2014
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), accepted in 2015
arXiv   project   slides   poster   code

Learning a Deep Convolutional Network for Image Super-Resolution
Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang
European Conference on Computer Vision (ECCV), 2014
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), accepted in 2015
arXiv   ECCV version   code

Optimized Product Quantization for Approximate Nearest Neighbor Search
Tiezheng Ge, Kaiming He, Qifa Ke, and Jian Sun
Computer Vision and Pattern Recognition (CVPR), 2013
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), accepted in 2013
paper   PAMI version   supp   code   project

Guided Image Filtering
Kaiming He, Jian Sun, and Xiaoou Tang
European Conference on Computer Vision (ECCV), 2010 (Oral)
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), accepted in 2012
paper   PAMI version   supp   code   slides   project

Single Image Haze Removal using Dark Channel Prior
Kaiming He, Jian Sun, and Xiaoou Tang
Computer Vision and Pattern Recognition (CVPR), 2009 (Oral). CVPR Best Paper Award
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), accepted in 2010
paper   PAMI version   images   slides   videos   project   thesis