Stars
Efficient and clean PyTorch reimplementation of "End-to-end Neural Coreference Resolution" (Lee et al., EMNLP 2017).
llama3 implementation one matrix multiplication at a time
[MathCoder, MathCoder-VL] Family of LLMs/LMMs for mathematical reasoning.
Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.
PrivacyGLUE: A Benchmark Dataset for General Language Understanding in Privacy Policies
The data represents financial transactions -- bank transfers, purchases, credit card transactions, checks, etc. Most of the transactions are legitimate. A few represent money laundering. The data i…
The AMLSim project is intended to provide a multi-agent based simulator that generates synthetic banking transaction data together with a set of known money laundering patterns - mainly for the pur…
Code & Data for "Tabular Transformers for Modeling Multivariate Time Series" (ICASSP, 2021)
Microsoft MakeCode editor for the LEGO MINDSTORMS EV3 Brick
A library for building & simulate your own sensors and devices compatible with the modern LEGO PoweredUp system.
Aggregation for complex labels, described in https://www.ischool.utexas.edu/~ml/papers/braylan_web2020.pdf
Data Mining Project - STIB network quality assessment code
State-of-the-Art Text Embeddings
STUMPY is a powerful and scalable Python library for modern time series analysis
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
A collection of datasets and tasks for legal machine learning
CRSLab is an open-source toolkit for building Conversational Recommender System (CRS).
Python library for knowledge graph embedding and representation learning.
I am trying to describe complex matters in simple doodles!
fast python port of arc90's readability tool, updated to match latest readability.js!
Complex neural network examples for Flux.jl
Latex code for making neural networks diagrams
A scikit-learn compatible library for graph kernels