Sara Pieri

I'm a research assistant in the Computer Vision department at MBZUAI under the supervision of Dr. Hisham Cholakkal.

I completed my MSc in Artificial Intelligence at MBZUAI. Prior to that, I earned a bachelor's degree in Computer Science Engineering from Sapienza Università di Roma in Italy.

Email  /  CV  /  Scholar  /  Linkedin  /  Twitter  /  Github

profile photo

Research

I'm interested in computer vision, natural language processing, machine learning and sustainability. Some of my research interests include multimodal learning, efficient architectures, federated learning, fairness and explainability.

BiMediX: Bilingual Medical Mixture of Experts LLM
Sara Pieri, Sahal Shaji Mullappilly, Fahad Shahbaz Khan, Rao Muhammad Anwer, Salman Khan, Timothy Baldwin, Hisham Cholakkal
arXiv / code / hf

Advancing llm models for medical question-answering and dialogue applications.

Handling Data Heterogeneity via Architectural Design for Federated Visual Recognition
Sara Pieri, Jose Renato Restom, Samuel Horvath, Hisham Cholakkal
NeurIPS, 2023
arXiv / code

An experimental study on how to achieve better performance in federated tasks using architectural design.

CellSDF: Exploring 2D Cell Shapes with Signed Distance Functions
Sara Pieri, Boulbaba Ben Amor, Hisham Cholakkal
In progress...

Learn cell shape contours through signed distance function (SDF) and associate them with latent codes to analyze cell morphology in low-dimensional spaces.

Blog Posts & Others

Here's a collection of my blog posts on interesting things I learned recently!

Build Your First Hugging Face Space with Gradio
Sara Pieri
Article

A tutorial on how to present your HF model in Spaces with Gradio.

Artificial Intelligence - Updates and Challenges with Short Stories
Sara Pieri
Slides (ITA)

Intellignza Artificiale - Brevi Storie (Volunteering 2023, Progress and Challenges of AI explained to young adults)


Feel free to steal this website's source code. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.