Collection of awesome test-time (domain/batch/instance) adaptation methods

Frouros: an open-source Python library for drift detection in machine learning systems.

Training Distribution Selection for Provable OOD Performance

Official implementation of NeurIPS 2025 paper "Visual Instruction Bottleneck Tuning"

Advanced domain adaptation techniques for robust machine learning across different data distributions

Reinforcement Learning Environments for Sustainable Energy Systems

A curated collection of Test-Time Adaptation (TTA) papers, methods, and resources, updated monthly with the latest research.

[TMLR 2025] Importance Weighting for Aligning Language Models under Deployment Distribution Shift

Code for the paper "Where are we with calibration under dataset shift in image classification?"

Official implementation of the Fréchet Radiomic Distance

Code for 'Automatic dataset shift identification to support root cause analysis of AI performance drift', MICCAI 2025

This repository contains the code of the distribution shift framework presented in A Fine-Grained Analysis on Distribution Shift (Wiles et al., 2022).

Lightweight, useful implementation of conformal prediction on real data.

Cuff-KT: Tackling Learners' Real-time Learning Pattern Adjustment via Tuning-Free Knowledge State-Guided Model Updating

A repository and benchmark for online test-time adaptation.

Official implementation of ICML 2025 paper "Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach"

A Python Library for Biquality Learning

[WWW2024 (Oral)] PyTorch implementation of "Intelligent Model Update Strategy for Sequential Recommendation".

GOOD: A Graph Out-of-Distribution Benchmark [NeurIPS 2022 Datasets and Benchmarks]