Pedro Sandoval's repositories
autoregressive-poisoning
Code for the paper "Autoregressive Perturbations for Data Poisoning" (NeurIPS 2022)
learn-from-unlearnable
Code for the paper "What Can We Learn from Unlearnable Datasets?" (NeurIPS 2023)
AdversarialQuerying
Code for "Interpretability for Prototypical Networks" (based on the repo for Adv Robust Few-Shot Learning)
synergy-algorithms
Algorithms for learning team compositions using synergy
advertorch
A Toolbox for Adversarial Robustness Research
CenterNet
An easy to understand version of CenterNet
ffcv-imagenet
Train ImageNet *fast* in 500 lines of code with FFCV
imagenet-c-p
Corruption and Perturbation Robustness (ICLR 2019)
mae
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
neural-anisotropy-directions
Source code for "Neural Anisotropy Directions"
pix2seq
Pix2Seq - A general framework for turning RGB pixels into semantically meaningful sequences
psandovalsegura.github.io
Personal website
Pytorch-Adversarial-Training-CIFAR
This repository provides simple PyTorch implementations for adversarial training methods on CIFAR-10.
pytorch-semseg
Semantic Segmentation Architectures Implemented in PyTorch
PyTorch-VAE
A Collection of Variational Autoencoders (VAE) in PyTorch.
Robust-Semantic-Segmentation
Robust Semantic Segmentation using AdvProp (a fork of DDC-AT)
robustness
A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.
ViT-CIFAR
PyTorch implementation for Vision Transformer[Dosovitskiy, A.(ICLR'21)] modified to obtain over 90% accuracy FROM SCRATCH on CIFAR-10 with small number of parameters (= 6.3M, originally ViT-B has 86M).