Matteo Pagliardini's repositories
Agree-to-Disagree
Repo for the paper: "Agree to Disagree: Diversity through Disagreement for Better Transferability"
Uncertainty-Driven-Perturbations
Repo for the paper: "Increasing the Classification Margin with Uncertainty Driven Perturbations"
GroovesharkRecommender
Experimenting collaborative filtering methods for artists recommendation.
Revisiting-ACVI
Code to reproduce experiments from the paper "Revisiting the ACVI method for Constrained Variational Inequalities"
Javascript-LDA
A node.js addon written in C++ allowing anyone to use powerful topic modeling methods from Javascript.
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
stanford_corenlp_pywrapper
The original `stanford_corenlp_pywrapper` lib modified to work with python3.
understanding-fast-adv-training
Understanding and Improving Fast Adversarial Training [NeurIPS 2020]