PastelBelem8

2019-CAADRIA-conflicting-goals-a-multi-objective-optimization-study

Knet.jl

Koç University deep learning framework.

unscrambler

NLP-based system whose goal is to recover corrupted files. To this end, we are given both a training and a test set, where the test set is assumed to be generated from the same distribution as the training set.

AdaFair

ADOPT.jl

This is the result of my master thesis on Multi-Objective Optimization. This repository is more focused towards Pareto-based optimization rather than SIngle-Objective optimization with preference articulation. We focus on time-consuming optimization routines and, as a result we focus on model-based methods to allow for faster convergence times. This is relevant for Architectural Design Optimization, which depends on time-intensive simulations (e.g. minutes, hours or even days to complete a single simulation).

BARTScore

BARTScore: Evaluating Generated Text as Text Generation

clinical-data-ml-metadata

Clinical ML metadata specification for columns found available in MIMIC and eICU datasets after being preprocessed with the YAIB-Cohort package.

deep-learning-from-scratch

dotfiles

Get ready for dotfiles. Contains i3, i3blocks, rofi, dunst, picom, vim, tmux, and zsh.

ecaade-2018-from-design-to-optimized-design

Results and scripts used to reproduce the analysis reported on the 2018 paper at eCAADe, whose title is "From Design to Optimized Design: An Algorithmic Approach".

gender-bias-diagnosis-benchmark

generative-calibration-lms

Calibration of autoregressive language models.

uci-statnlp

Code for the StatNLP course homework.

Flux.jl

Relax! Flux is the ML library that doesn't make you tensor

handwritten-recognition-and-detection

Repository concerning the creation of a system capable of detecting handwritting and recognizing its content. This system will be applied to images involving visual elements other than just handwritting.

iterative-rectangles

Khepri

Khepri is an algorithmic design tool that integrates design, analysis, and optimization.

LightGBM

A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.

marginalization

Source code for the ACL'23 paper "Should you marginalize over possible tokenizations?"

ml4nlp-cogsci-summer22

Course materials for the Machine Learning for NLP course taught by Sameer Singh for the Cognitive Science summer school 2022.

openlogprobs

Extract full next-token probabilities via language model APIs

pastelbelem8.github.io

Catarina's personal webpage (adapted from al-folio Jekyll template).

Platypus

A Free and Open Source Python Library for Multiobjective Optimization

PyTorch-VAE

A Collection of Variational Autoencoders (VAE) in PyTorch.

rosetta

The Generative Design Tool

ScikitLearn.jl

Julia implementation of the scikit-learn API

t-few

Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"

treetree2-hac-project-example

ucimlrepo

Python package for dataset imports from UCI ML Repository

zafar-fair-classification

Refactor upon Zafar's fair classification bias mitigation method.