JonasGeiping

cramming

Cramming the training of a (BERT-type) language model into limited compute.

breaching

Breaching privacy in federated learning scenarios for vision and text

invertinggradients

Algorithms to recover input data from their gradient signal through a neural network

poisoning-gradient-matching

Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching

data-poisoning

Implementations of data poisoning attacks against neural networks and related defenses.

carving

Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives

fullbatchtraining

Training vision models with full-batch gradient descent and regularization

dataaugs

ParametricMajorization

New training strategies for energy minimization methods with learnable parameters (ICCV 2019)

poisoning-benchmark

A unified benchmark problem for data poisoning attacks

torchlmdb

LMDB wrapper for pytorch datasets.

flexBox

FlexBox is a fexible MATLAB toolbox for finite dimensional convex variational problems in image processing and beyond.

dleval

New and fancy exercises evaluation system for the "Deep Learning" course!

flash-attention

Fast and memory-efficient exact attention

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

jonasgeiping.github.io

keras-applications

Reference implementations of popular deep learning models.

lm-watermarking

prost

webpage

website

📝 Easily create a beautiful website using Hugo, GitHub, and Netlify