Federico Bianchi's starred repositories
mechanistic-error-probe
A mechanistic approach for understanding and detecting factual errors of large language models.
safety-tuned-llamas
ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.
silviatti.github.io
:triangular_ruler: Jekyll theme for building a personal site, blog, project documentation, or portfolio.
exaggerated-safety
Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
plip
Pathology Language and Image Pre-Training (PLIP) is the first vision and language foundation model for Pathology AI (Nature Medicine). PLIP is a large-scale pre-trained model that can be used to extract visual and language features from pathology images and text description. The model is a fine-tuned version of the original CLIP model.
quack-reduce
A playground for running duckdb as a stateless query engine over a data lake
e-pluribus-unum-evalrs-2022
Repo containing code and data for the analysis presented in: "E Pluribus Unum: Guidelines on Multi-Objective Evaluation of Recommender Systems"
evalRS-KDD-2023
Official Repository for EvalRS @ KDD 2023: a Rounded Evaluation of Recommender Systems
vision-language-models-are-bows
Experiments and data for the paper "When and why vision-language models behave like bags-of-words, and what to do about it?" Oral @ ICLR 2023
fashion-clip
FashionCLIP is a CLIP-like model fine-tuned for the fashion domain.
logseq-plugin-agenda
A calendar, task manager and daily planner plugin for logseq
evalRS-CIKM-2022
Official Repository for EvalRS @ CIKM 2022: a Rounded Evaluation of Recommender Systems
post-modern-stack
Joining the modern data stack with the modern ML stack