collaborators

6 papers

cs.LG2025

The Deleuzian Representation Hypothesis

Clément Cornet, Romaric Besançon, Hervé Le Borgne

We propose an alternative to sparse autoencoders (SAEs) as a simple and effective unsupervised method for extracting interpretable concepts from neural networks. The core idea is t…

cs.CL2025

ManufactuBERT: Efficient Continual Pretraining for Manufacturing

Robin Armingaud, Romaric Besançon

While large general-purpose Transformer-based encoders excel at general language understanding, their performance diminishes in specialized domains like manufacturing due to a lack…

cs.CL2025

GLiDRE: Generalist Lightweight model for Document-level Relation Extraction

Robin Armingaud, Romaric Besançon

Relation Extraction (RE) is a fundamental task in Natural Language Processing, and its document-level variant poses significant challenges, due to complex interactions between enti…

cs.CV2025

Explaining How Visual, Textual and Multimodal Encoders Share Concepts

Clément Cornet, Romaric Besançon, Hervé Le Borgne

Sparse autoencoders (SAEs) have emerged as a powerful technique for extracting human-interpretable features from neural networks activations. Previous works compared different mode…

cs.CL2024

From LIMA to DeepLIMA: following a new path of interoperability

Victor Bocharov, Romaric Besançon, Gaël de Chalendar +2

In this article, we describe the architecture of the LIMA (Libre Multilingual Analyzer) framework and its recent evolution with the addition of new text analysis modules based on d…

cs.CV2024

Automatic Die Studies for Ancient Numismatics

Clément Cornet, Héloïse Aumaître, Romaric Besançon +3

Die studies are fundamental to quantifying ancient monetary production, providing insights into the relationship between coinage, politics, and history. The process requires tediou…