A Python library for comparing forecast accuracy between different models using statistical tests.

🤗 Benchmark Large Language Models Reliably On Your Data

Official Repository for "Communication Efficient Federated Learning with Generalized Heavy-Ball Momentum", accepted at TMLR 2025

🚀 Lightning-fast computer vision models. Fine-tune SOTA models with just a few lines of code. Ready for cloud ☁️ and edge 📱 deployment.

[CVPR 2025 Highlight] Official repository for the paper: "SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation"

Anthropic Economix Index

Hack the Act! is a RAG-based chatbot designed to demystify the European Union AI Act

Refine high-quality datasets and visual AI models

DomainBed is a suite to test domain generalization algorithms

Code for the paper "Attention Meets Post-hoc Interpretability: A Mathematical Perspective", ICML 2024

Interface to stable-baselines3 APIs for training RL policies on gym-registered environments

PaintNet: Unstructured Multi-Path Learning from 3D Point Clouds for Robotic Spray Painting

DROPO: Sim-to-Real Transfer with Offline Domain Randomization

Domain Randomization via Entropy Maximization

Faithful and Robust Local Interpretability for Textual Predictions

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Flower: A Friendly Federated AI Framework

A Google weather forecast clone

Code for the paper "SMACE: A New Method for the Interpretability of Composite Decision Systems", ECML 2022

Code for the paper "Comparing Feature Importance and Rule Extraction for Interpretability on Text Data", XAIE @ ICPR 2022

Code for the paper "A Sea of Words: An In-Depth Analysis of Anchors for Text Data", AISTATS 2023

Hyperspherical classification for Multi-source Open-Set domain adaptation

Rotation-based Open Set

A new multi-modal TTA approach, called RNA++, combined with a new set of losses (CR losses) aiming at reducing classifier’s uncertainty

N-EPIC-Kitchens: The event-based camera extension of the large-scale EPIC-Kitchens dataset.

🔍 Explore Egocentric Vision: research, data, challenges, real-world apps. Stay updated & contribute to our dynamic repository! Work-in-progress; join us!

Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning