https://github.com/agathesenellart/summer_school_ai_science_2025
This repository contains the material for the tutorial session on Multimodal Variational Autoencoders for the Summer School AI+Science 2025.
https://github.com/agathesenellart/summer_school_ai_science_2025
Science Score: 49.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 1 DOI reference(s) in README -
✓Academic publication links
Links to: arxiv.org, biorxiv.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (10.5%) to scientific vocabulary
Repository
This repository contains the material for the tutorial session on Multimodal Variational Autoencoders for the Summer School AI+Science 2025.
Basic Info
- Host: GitHub
- Owner: AgatheSenellart
- Language: Jupyter Notebook
- Default Branch: main
- Size: 818 KB
Statistics
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Multimodal VAEs tutorial
This repository contains the material for the tutorial session on Multimodal Variational Autoencoders for the Summer School AI+Science 2025.
For this tutorial, you can either:
1. Run the notebook in a local environment on your computer. See instructions here.
2. Run the notebook on Google Colab : 
Running the tutorial on your computer
Download the code from github:
Uncompress the folder and move into it.
Into a python environment with python 3.11 run:
pip install multivae && pip install huggingface_hubSelect this environment for running the notebook.
After the session
The complete solution notebook will be uploaded on this page as well as the slides.
To know more about the different multimodal VAEs methods that exists, you can look at this survey paper. Short descriptions of models are also available in MultiVae's documentation.
Which model should I use in my application ? : This benchmark case study can help you decide. Note that many models can be trained on incomplete datasets including the ones used in this tutorial.
What are the medical applications of multimodal VAEs ? : These models can be used to generate synthetic medical images as done in (Reuben et al, 2025), to augment or complete a dataset, or for anomaly detection as done in (Aguila et al 2023) and (Kumar et al, 2024).
If you have any question or feed-back, don't hesitate to reach out to agathe.senellart@inria.fr !
Owner
- Login: AgatheSenellart
- Kind: user
- Repositories: 12
- Profile: https://github.com/AgatheSenellart
GitHub Events
Total
- Watch event: 1
- Push event: 6
- Create event: 2
Last Year
- Watch event: 1
- Push event: 6
- Create event: 2