1 citations · 1 across the 10 of their papers we have counts for
15 papers
An Empirical Study of Recent Large Language Models for Knowledge Graph to Text Generation on Standard Benchmarks
Priyanka, Renaud Delbru, Souhail Bakkali +2
Knowledge graph-to-text (KG-to-text) generation verbalizes a set of knowledge graph triples into fluent natural language. While fine-tuned encoder-decoder models have long been the…
Structured Visual Target Learning For Cross-Subject eeg-to-image retrieval
Salini Yadav, Taveena Lotey, Mickaël Coustaty +2
Cross-subject EEG-to-image retrieval requires a neural represen- tation trained on source subjects to remain aligned with a visual embedding space for an unseen subject. Whereas ex…
Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking
Tien Nam Nguyen, Emanuela Boros, Ahmed Hamdi +3
Large language models (LLMs) have recently shown promise for historical entity linking, but preference optimization for this task is often formulated with only one negative candida…
When Superpixels Fail on Documents: A Study of Segmentation for LIME Explanations
Quentin Telnoff, Emanuela Boros, Mickaël Coustaty +3
Post-hoc explanation methods are widely used to inspect image classifiers, but their reliability depends on design choices that are often treated as implementation details. We stud…
Active Learning for Cascaded Object Detection: Balancing Coverage and Uncertainty in Table Extraction Pipelines
Eliott Thomas, Mickael Coustaty, Aurelie Joseph +3
Table extraction from business documents relies on a cascaded pipeline where Table Detection (TD) first localizes tables and Table Structure Recognition (TSR) then recovers their i…
ConRTF: Edge-Constrained Boundary Distribution Refinement for Realtime TransFormer Table Structure Recognition
Eliott Thomas, Tri-Cong Pham, Mickael Coustaty +5
Table Structure Recognition (TSR) aims to recover the row and column layout of tables from document images, a key step in document understanding pipelines. Accurate TSR depends on…
DocQT: Improving Document Forgery Localization Robustness via Diverse JPEG Quantization Tables
Kylian Ronfleux-Corail, Guillaume Bernard, Mickaël Coustaty +1
Document manipulation localization models achieve strong performance on public benchmarks yet fail to generalize to operational document workflows. We identify a critical and overl…
Neurosymbolic Information Extraction from Transactional Documents
Arthur Hemmer, Mickaël Coustaty, Nicola Bartolo +1
This paper presents a neurosymbolic framework for information extraction from documents, evaluated on transactional documents. We introduce a schema-based approach that integrates…
Evaluating the Impact of Khmer Font Types on Text Recognition
Vannkinh Nom, Souhail Bakkali, Muhammad Muzzamil Luqman +2
Text recognition is significantly influenced by font types, especially for complex scripts like Khmer. The variety of Khmer fonts, each with its unique character structure, present…
QUEST: Quality-aware Semi-supervised Table Extraction for Business Documents
Eliott Thomas, Mickael Coustaty, Aurelie Joseph +4
Automating table extraction (TE) from business documents is critical for industrial workflows but remains challenging due to sparse annotations and error-prone multi-stage pipeline…
RAPTOR: Refined Approach for Product Table Object Recognition
Eliott Thomas, Mickael Coustaty, Aurelie Joseph +4
Extracting tables from documents is a critical task across various industries, especially on business documents like invoices and reports. Existing systems based on DEtection TRans…
KhmerST: A Low-Resource Khmer Scene Text Detection and Recognition Benchmark
Vannkinh Nom, Souhail Bakkali, Muhammad Muzzamil Luqman +2
Developing effective scene text detection and recognition models hinges on extensive training data, which can be both laborious and costly to obtain, especially for low-resourced l…
LLMChain: Blockchain-based Reputation System for Sharing and Evaluating Large Language Models
Mouhamed Amine Bouchiha, Quentin Telnoff, Souhail Bakkali +4
Large Language Models (LLMs) have witnessed rapid growth in emerging challenges and capabilities of language understanding, generation, and reasoning. Despite their remarkable perf…
IDTrust: Deep Identity Document Quality Detection with Bandpass Filtering
Musab Al-Ghadi, Joris Voerman, Souhail Bakkali +3
The increasing use of digital technologies and mobile-based registration procedures highlights the vital role of personal identity documents (IDs) in verifying users and safeguardi…
Lazy-k: Decoding for Constrained Token Classification
Arthur Hemmer, Mickaël Coustaty, Nicola Bartolo +2
We explore the possibility of improving probabilistic models in structured prediction. Specifically, we combine the models with constrained decoding approaches in the context of to…