← Search

Firas Gabetni

2 accepted papers

2026

Ensembling Pruned Attention Heads For Uncertainty-Aware Efficient Transformers

ICLR 2026poster

Uncertainty quantification (UQ) is essential for deploying deep neural networks in safety-critical settings. Although methods like Deep Ensembles achieve strong UQ performance, their high computational and memory costs hinder scalability to large models. We introduce Hydra Ensembles, an efficient tr…

Cited by 0SourceScholar
2025

Torch-Uncertainty: Deep Learning Uncertainty Quantification

NeurIPS 2025spotlight

Deep Neural Networks (DNNs) have demonstrated remarkable performance across various domains, including computer vision and natural language processing. However, they often struggle to accurately quantify their predictions' uncertainty, limiting their broader adoption in critical industrial applicati…

Cited by 0SourcecodeScholar