Ensuring accessibility for individuals with cognitive impairments is essential for autonomy, self-determination, and full citizenship. However, manual Easy-to-Read (ETR) text adaptations are slow, costly, and difficult to scale, limiting access to crucial information in healthcare, education, and civic life. AI-driven ETR generation offers a scalable solution but faces key challenges, including dataset scarcity, domain adaptation, and balancing lightweight learning of Large Language Models (LLMs). In this paper, we introduce ETR-fr, the first dataset for ETR text generation fully compliant with European ETR guidelines. We implement parameter-efficient fine-tuning on PLMs and LLMs to establish generative baselines. To ensure high-quality and accessible outputs, we introduce an evaluation framework based on automatic metrics supplemented by human assessments. The latter is conducted using a 36-question evaluation form that is aligned with the guidelines. Overall results show that PLMs perform comparably to LLMs and adapt effectively to out-of-domain texts. Code and datasets are available at https://github.com/FrLdy/ETR-fr.

Simplifying complex texts is essential to ensure equitable access to information, particularly for individuals with cognitive impairments.The Easy-to-Read (ETR) initiative provides a framework to make content more accessible for these individuals.However, manually creating such texts remains time-consuming and resourceintensive.In this work, we investigate the potential of large language models (LLMs) to automate the generation of ETR content.To address the scarcity of aligned corpora and the specific constraints of ETR, we propose a multitask learning (MTL) approach that trains models jointly on text summarization, text simplification, and ETR generation.We explore two complementary strategies: multi-task retrievalaugmented generation (RAG) for in-context learning (ICL), and MTL-LoRA for parameterefficient fine-tuning (PEFT).Our experiments with Mistral-7B and LLaMA-3-8B, conducted on ETR-fr, a new high-quality dataset, show that MTL-LoRA consistently outperforms all other strategies in in-domain settings, while the MTL-RAG-based approach achieves better generalization in out-of-domain scenarios.

Despite the maturity of anomaly detection in structured and image data, anomaly detection in text remains surprisingly under-explored. Existing methods struggle with two key challenges: manifold collapse in high-dimensional language embeddings, and semantic entanglement that obscures contextual anomalies. We address both with the Robust Local AutoEncoder (RLAE), which combines robust subspace recovery with local geometry preservation. It allows to learn disentangled and anomaly-sensitive representations. We extend this to RoSAE, an ensemble of randomly pruned RLAEs that enhances robustness through architectural diversity. We introduce TAC which is the first benchmark framework to distinguish anomaly types in text, using topic hierarchies to separate independent from contextual anomalies for fair and reproducible evaluation. TAC resolves inconsistencies in prior benchmarks. RoSAE consistently outperforms state-of-the-art baselines across eight diverse corpora (6 more than state-of-the-art approaches), particularly under challenging contextual settings. Our results highlight the importance of both local structure and ensemble diversity in textual anomaly detection, and position RoSAE as a robust, scalable, and efficient method for tackling both independent and contextual anomalies.

As Picasso said, a painting lives only through the one who looks at it. To materialize this thought, we propose to automatically produce artworks that visually transform paintings by amplifying and distorting the most observed areas by viewers. Our work is based on a study conducted at the Caen Museum of Fine Arts in France. During the study, 151 participants were equipped with eye-tracking glasses, and observed various paintings, first alone and then in pairs. Based on the fixation and gaze path stored data, we first generate saliency maps that reflect the visual attention given to each painting. These maps are then used to fine-tune the UNETRSal model, a neural network designed to predict saliency maps, in order to align its outputs with human visual patterns observed during the experiment. The saliency maps generated are subsequently used to create deformations of the original painting. This overall process gives rise to a new artwork born from the interaction between human gaze and AI-prediction.