Popular GitHub Repositories for Uncertainty Quantification

Lightweight, useful implementation of conformal prediction on real data.

Open-source framework for uncertainty and deep learning models in PyTorch :seedling:

A Python toolbox for conformal prediction research on deep learning models, using PyTorch.

DeepHyper: Scalable Asynchronous Neural Architecture and Hyperparameter Search for Deep Neural Networks

Uncertainty Quantification 360 (UQ360) is an extensible open-source toolkit that can help you estimate, communicate and use uncertainty in machine learning model predictions.

Lightning-UQ-Box: Uncertainty Quantification for Neural Networks with PyTorch and Lightning

Conformal prediction for time-series applications.

Official repository for the paper "Masksembles for Uncertainty Estimation" (CVPR 2021).

Uncertainty Quantification over Graph with Conformalized Graph Neural Networks (NeurIPS 2023)

Helping AI practitioners better understand their datasets and models in text classification. From ServiceNow.

Fast uncertainty quantification for scientific machine learning (SciML) and differential equations

A variational inference method with accurate uncertainty estimation. It uses a new semi-implicit variational family built on neural networks and hierarchical distribution (ICML 2018).

Model zoo for different kinds of uncertainty quantification methods used in Natural Language Processing, implemented in PyTorch.

?A curated list of papers on the uncertainty in multi-modal large language model (MLLM).

[WACV2024] Official PyTorch implimentation for ``Active Transfer Learning for Efficient Video-Specific Human Pose Estimation''

ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models

Code for Paper: Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data

Code for "BayesAdapter: Being Bayesian, Inexpensively and Robustly, via Bayeisan Fine-tuning"

This is a community-driven collection of resources around amortized inference.

Distributional Gradient Boosting Machines