Latest Publications
DIVE-Doc: Downscaling foundational Image Visual Encoder into hierarchical architecture for DocVQA
In the DocVQA context, current end-to-end models either use lightweight architectures that run efficiently on small devices but have limited performance or rely on LVLMs that achieve high performance at significant computational cost. Thus, we present DIVE-Doc, an end-to-end […]
PRISM: Pruning for Rank-adaptive Interpretable Segmentation Model with Application to Historical Document Multiband Images
Multispectral (MS) imaging reveals latent content in historical documents by leveraging material-specific spectral signatures. Low-rank decompositions such as Nonnegative Matrix Factorization (NMF) effectively extract these components, but selecting the appropriate rank remains an open challenge in unsupervised settings. We […]
Converging Game Theory and Reinforcement Learning For Industrial Internet-of-Things
The fifth-generation (5G) wireless network provides high-rate, ultra-low latency, and high-reliability connections that can meet the Industrial Internet of Things (IIoT) requirements in factory automation, especially for robot motion control. In this paper, we address 5G service provisioning in an […]
Monitoring and Measurement System for Green Operation of Geographically Distributed ICT Services
Despite recent efforts and important results already achieved, the reduction of energy consumption and carbon emissions by Information and Communication Technologies is still far from the expected goals. As the annual growth in traffic is doubling every two years with […]
