6 papers
MICE: Minimal Interaction Cross-Encoders for efficient Re-ranking
Mathias Vast, Victor Morand, Basile van Cooten +3
Cross-encoders deliver state-of-the-art ranking effectiveness in information retrieval, but have a high inference cost. This prevents them from being used as first-stage rankers, b…
ToMMeR -- Efficient Entity Mention Detection from Large Language Models
Victor Morand, Nadi Tomeh, Josiane Mothe +1
Identifying which text spans refer to entities - mention detection - is both foundational for information extraction and a known performance bottleneck. We introduce ToMMeR, a ligh…
Fusion-CAM: Integrating Gradient and Region-Based Class Activation Maps for Robust Visual Explanations
Hajar Dekdegue, Moncef Garouani, Josiane Mothe +1
Interpreting the decision-making process of deep convolutional neural networks remains a central challenge in achieving trustworthy and transparent artificial intelligence. Explain…
Reproducing and Comparing Distillation Techniques for Cross-Encoders
Victor Morand, Mathias Vast, Basile Van Cooten +3
Recent advances in Information Retrieval have established transformer-based cross-encoders as a keystone in IR. Recent studies have focused on knowledge distillation and showed tha…
Curriculum Multi-Task Self-Supervision Improves Lightweight Architectures for Onboard Satellite Hyperspectral Image Segmentation
Hugo Carlesso, Josiane Mothe, Radu Tudor Ionescu
Hyperspectral imaging (HSI) captures detailed spectral signatures across hundreds of contiguous bands per pixel, being indispensable for remote sensing applications such as land-co…
On the Representations of Entities in Auto-regressive Large Language Models
Victor Morand, Josiane Mothe, Benjamin Piwowarski
Named entities are fundamental building blocks of knowledge in text, grounding factual information and structuring relationships within language. Despite their importance, it remai…