Pinned Repositories
constructed-datasets
Datasets for the paper "Adversarial Examples are not Bugs, They Are Features"
robustness
A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.
dp_data_synthesis
Draft of manuscript for configuration-free DP data synthesis
IAP_InterpretabilityClass
open_clip
An open source implementation of CLIP.
ShibaniSanturkar.github.io
soft-prompt-tuning
tensorlayer
TensorLayer: Reinforcement Learning and Deep Learning Library for Researcher and Engineer.
unrolled_gan
Unrolled Generative Adversarial Networks
helm
Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110). This framework is also used to evaluate text-to-image models in Holistic Evaluation of Text-to-Image Models (HEIM) (https://arxiv.org/abs/2311.04287).
ShibaniSanturkar's Repositories
ShibaniSanturkar/IAP_InterpretabilityClass
ShibaniSanturkar/dp_data_synthesis
Draft of manuscript for configuration-free DP data synthesis
ShibaniSanturkar/open_clip
An open source implementation of CLIP.
ShibaniSanturkar/ShibaniSanturkar.github.io
ShibaniSanturkar/soft-prompt-tuning
ShibaniSanturkar/tensorlayer
TensorLayer: Reinforcement Learning and Deep Learning Library for Researcher and Engineer.
ShibaniSanturkar/unrolled_gan
Unrolled Generative Adversarial Networks