← Search

Nacim Belkhir

2 accepted papers

2025

Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation

CVPR 2025poster

Uncertainty quantification in text-to-image (T2I) generative models is crucial for understanding model behavior and improving output reliability. In this paper, we are the first to quantify and evaluate the uncertainty of T2I models with respect to the prompt. Alongside adapting existing approaches…

2024

NECO: NEural Collapse Based Out-of-distribution detection

ICLR 2024poster

Detecting out-of-distribution (OOD) data is a critical challenge in machine learning due to model overconfidence, often without awareness of their epistemological limits. We hypothesize that "neural collapse", a phenomenon affecting in-distribution data for models trained beyond loss convergence, al…