Dr. Kaiming He
MIT EECS
Associate Professor of EECS at MIT and former Research Director at Meta FAIR. Inventor of Deep Residual Learning (ResNet, the most cited computer science paper of the 21st century with over 200,000 citations), Mask R-CNN, Momentum Contrast (MoCo), and Masked Autoencoders (MAE).
Areas of focus
Professional niches
Proof of Work
Masked Autoencoders Are Scalable Vision Learners (MAE)
Developed Masked Autoencoders (MAE), proving that masking 75% of image patches and using an asymmetric vision transformer autoencoder allows models to learn rich visual representations self-supervised at massive scale.
Requires substantial pre-training compute and large unlabeled image datasets for optimal self-supervised convergence.
Context: Vision Transformer (ViT-Large/Huge), asymmetric encoder-decoder, 75% random masking.
View missionDeep Residual Learning for Image Recognition (ResNet)
First author of the CVPR 2016 Best Paper introducing identity skip connections (Residual Networks), overcoming vanishing gradients to train 100+ layer networks, which became standard across all modern deep learning and transformers.
Pure convolutional ResNets possess localized receptive fields, necessitating hybrid attention blocks for global context modeling.
Context: Skip connections (x + F(x)), Batch Normalization, ResNet-50/101/152 architectures.
View mission