Stars
Unattended Lightweight Text Classifiers with State-of-the-Art LLM Embeddings
Align your LM to express calibrated verbal statements of confidence in its long-form generations.
Awesome Incremental Learning
A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/
Visual, Interactive Articles About Machine Learning: https://mlu-explain.github.io/
Toolbox for molecular animations in Blender, powered by Geometry Nodes.
A collection of visual guides to help applied scientists learn causal inference.
Toolkit for creating, sharing and using natural language prompts.
Mistral: A strong, northwesterly wind: Framework for transparent and accessible large-scale language model training, built with Hugging Face 🤗 Transformers.
A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.
Simple modular codebase that makes it easy to plug in new datasets, models, or configs while keeping track of experiments.
pipreqs - Generate pip requirements.txt file based on imports of any project. Looking for maintainers to move this project forward.
disentanglement_lib is an open-source library for research on learning disentangled representations.
This repository contains the full code for our paper "Theory and evaluation metrics for learning disentangled representations"
A platform for managing machine learning experiments
Code and resources on scalable and efficient Graph Neural Networks
Gaussian Processes and Statistical Decision-making in Non-Euclidean Spaces
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
This repository contains data readers and examples for the three tracks of the Shifts Dataset and the Shifts Challenge.
Official PyTorch implementation of 🏁 MFCVAE 🏁: "Multi-Facet Clustering Variatonal Autoencoders (MFCVAE)" (NeurIPS 2021). A class of variational autoencoders to find multiple disentangled clustering…
Code for "Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning"
The Compositional Perturbation Autoencoder (CPA) is a deep generative framework to learn effects of perturbations at the single-cell level. CPA performs OOD predictions of unseen combinations of dr…
Standardizing weights to accelerate micro-batch training
Unofficial PyTorch Reimplementation of RandAugment.
Execute a local command using the processing power of another Linux machine.
Implementation of Lie Transformer, Equivariant Self-Attention, in Pytorch
Notes for courses taken at Harvard (2015--2019)