Implementation Catalog

Benchmarking VLMs with Social-Cue News Images and LLM-as-Judge Assessment - evaluates how vision-language models handle real news images containing demographic and social attributes

Competing Risks Interpretable Survival Prediction with Neural Additive Models

An AI-powered tool designed to analyze bias in text and visual content, with a focus on risk identification, mitigation, and promoting sustainable and trustworthy AI systems

An open-source framework for fine-tuning retrieval-augmented generation (RAG) systems across centralized and federated architectures with comprehensive support for state-of-the-art RAG fine-tuning methods.

A benchmark suite for evaluating Large Multimodal Models on seven Human-Centered AI principles: Fairness, Ethics, Understanding, Reasoning, Language Inclusivity, Empathy, and Robustness

A repository providing reference implementations and resources for the 2025 Bootcamp on Interpretable and Explainable AI, covering both post-hoc explainability methods and interpretable models

A comprehensive framework for Knowledge Graph Retrieval Augmented Generation (KG-RAG).

A benchmark for evaluating fairness and performance of Large Multimodal Models on multilingual Visual Question Answering tasks across 11 languages and 5 social attributes

A privacy-preserving framework for LLM-based text-to-SQL that uses schema masking and progressive unmasking to protect sensitive database information while maintaining query accuracy

A Model Context Protocol (MCP) server that curates positive news stories using AI-powered sentiment analysis, integrating with Claude Desktop to deliver uplifting news

A toolkit for facilitating MIA resiliency testing on diffusion-model-based synthetic tabular data

A Shared Encoder Approach to Multimodal Representation Learning

A repository with reference implementations for deploying AI models in production environments, focusing on best practices and cloud-native solutions.

Library for handling atomistic graph datasets focusing on transformer-based implementations, with utilities for training various models, experimenting with different pre-training tasks, and a suite of pre-trained models with huggingface integrations

A repository for social bias mitigation in LLMs using machine unlearning

A toolkit for facilitating research and deployment of ML models for healthcare

A repository with demos for various diffusion models for tabular and time series data

A repository with implementations advanced fine-tuning techniques and approaches to enhance Large Language Model performance, reduce their computational cost, with a focus on alignment with human values

A flexible, modular, and easy to use library to facilitate federated learning research and development in healthcare settings

A platform to launch and monitor Federated Learning (FL) training jobs, designed to bridge the gap between FL algorithm implementations and practical healthcare applications

A toolkit for research on multimodal representation learning

A comprehensive library for developing foundation models using Electronic Health Record (EHR) data, with a focus on advanced medical data processing and modeling

A toolkit to download, augment, and benchmark Open-PMC data

A repository reference implementations for retrieval-augmented generation

A repository with reference implementations of self-supervised learning techniques

Simple and computationally efficient neural network uncertainty estimation via Variational Bayesian Last Layers - a deterministic variational approach for Bayesian last layers with quadratic complexity in last layer width

Efficient LLM inference on Slurm clusters using vLLM

A repository with implementation of anomaly detection techniques

A reinforcement learning solution for HVAC temperature control designed to minimize energy consumption in data centers and buildings. Available as the 'hnp' package on PyPI.

A repository with implementations of recommender systems

A repository with implementations of privacy-enhancing techniques for machine learning