Research Scientist MIT CSAIL, Co-Founder @TransluceAI. MIT work at @multimodal-interpretability
Stars
6
stars
written in Python
Clear filter
Refine high-quality datasets and visual AI models
Pytorch-based tools for visualizing and understanding the neurons of a GAN. https://gandissect.csail.mit.edu/
Pretrained Image & Video ConvNets and GANs for PyTorch: NASNet, ResNeXt (2D + 3D), ResNet (2D + 3D), InceptionV4, InceptionResnetV2, Xception, DPN, NonLocalNets, R(2+1)D nets, MultiView CNNs, Tempo…
A toolkit for describing model features and intervening on those features to steer behavior.
Nearest Neighbor Normalization (EMNLP 2024)




