bezirganyan/DBF_uncertainty

Original PyTorch implementation of AIStats 2025 paper: Multimodal Learning with Uncertainty Quantification based on Discounted Belief Fusion

30
/ 100
Emerging

This is a research project for AI/ML practitioners working on multimodal learning. It helps by providing a PyTorch implementation for combining information from different data sources (like images and text) while also quantifying how certain the model is about its predictions. You input multimodal datasets, and it outputs model training results and uncertainty metrics. This is for researchers and advanced practitioners developing new machine learning models.

No commits in the last 6 months.

Use this if you are a machine learning researcher exploring novel methods for fusing multimodal data and need to understand the uncertainty in your model's predictions.

Not ideal if you are looking for a plug-and-play solution for a business problem or a library with high-level APIs for immediate application.

multimodal-data-fusion uncertainty-quantification deep-learning-research model-confidence AI-development
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

10

Forks

1

Language

Python

License

GPL-3.0

Last pushed

Sep 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/bezirganyan/DBF_uncertainty"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.