← Search

Laure Berti-Equille

2 accepted papers

2025

Multimodal Learning with Uncertainty Quantification based on Discounted Belief Fusion

AISTATS 2025poster

Multimodal AI models are increasingly used in fields like healthcare, finance, and autonomous driving, where information is drawn from multiple sources or modalities such as images, texts, audios, videos. However, effectively managing uncertainty—arising from noise, insufficient evidence, or conflic…

Cited by 0SourcecodeScholar
2024

Faithful Vision-Language Interpretation via Concept Bottleneck Models

ICLR 2024poster

The demand for transparency in healthcare and finance has led to interpretable machine learning (IML) models, notably the concept bottleneck models (CBMs), valued for their potential in performance and insights into deep neural networks. However, CBM's reliance on manually annotated data poses chall…

Cited by 35SourcePDFScholar