Comprehensive and Rigorous Framework for Reproducible Recommender Systems Evaluation

AMIUGraph: Analysis and Modeling of Interactions for Utility-driven Benchmarking of Graph-Based Models in Healthcare

This is the official repository for the paper "A Reproducible and Fair Evaluation of Partition-aware Collaborative Filtering". (revision state)

A Python Library for Standardized and Reproducible Data Management in Recommender Systems

Ducho is a Python framework aimed to extract multimodal features used in multimodal recommendation settings through a highly-customizable processing and extraction pipeline.

GradeSQL is a framework to generate training datasets and train Outcome Reward Models (ORMs) that score and rank LLM-generated SQL, offering an alternative to execution-based BoN and Majority Voting, with pipelines and benchmarks (Spider, BIRD).

Source code for the paper "Type-Less yet Type-Aware Inductive Link Prediction with Pretrained Language Models" accepted to EMNLP 2025