Publications

• Communication dans un congrès

Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification

Abdellah Zakaria Sellam, Salah Eddine Bekhouche, Cosimo Distante, Abdelmalik Taleb-Ahmed

Art style classification remains a formidable challenge in computational aesthetics due to the scarcity of expertly labeled datasets and the intricate, often nonlinear interplay of stylistic elements. While recent dual-teacher self-supervised frameworks reduce reliance on labeled data, their linear…

Image Analysis and Processing – ICIAP 2025, Sep 2025, Rome, Italy. pp.401-412, ⟨10.1007/978-3-032-10192-1_33⟩. ⟨hal-05700776⟩

• Communication dans un congrès

DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images

Mamadou Keita, Wassim Hamidouche, Hessen Bougueffa Eutamene, Abdelmalik Taleb-Ahmed, Abdenour Hadid

This paper introduces DeeCLIP, a novel framework for detecting AI-generated images using CLIP-ViT and fusion learning. Despite significant advancements in generative models capable of creating highly photorealistic images, existing detection methods often struggle to generalize across different…

Advanced Concepts for Intelligent Vision Systems (ACIVS 2025), Jun 2025, Tokyo, Japan. pp.146-158, ⟨10.1007/978-3-032-07343-3_12⟩. ⟨hal-05473197⟩

• Communication dans un congrès

Single-Path Precision: Differentiable Bit-Width & Numeric-Format Learning for FPGA-Efficient Neural Networks

Emanuel Trabes, Kawthar Dellel, Carlos Valderrama, Abdelmalik Taleb-Ahmed

Quantization in neural networks typically requires early commitment to a fixed numerical format—either fixed-point or floating-point—and a limited set of word sizes supported by the target hardware. This rigid choice often compromises either model accuracy or hardware efficiency. While FPGAs offer…

23rd International Conference on Image Analysis and Processing, Sep 2025, Rome, Italy. pp.424-435, ⟨10.1007/978-3-032-10192-1_35⟩. ⟨hal-05700748⟩

• Article dans une revue

Mo-enhanced passivity of stainless steels studied at metal/oxide interfaces by DFT atomistic modeling

Xian Huang, Dominique Costa, Vincent Maurice, Philippe Marcus

Applied Surface Science, 2026, 716, ⟨10.1016/j.apsusc.2025.164709⟩. ⟨hal-05322240⟩

• Article dans une revue

Silicon Tile-Stacking Technology for Low-Loss Sub-THz Waveguides and 3D Packaging

Arthur L. Alves, Cybelle Belem Goncalves, Frederic Gianesello, Guillaume Ducournau, Emmanuel Dubois

This paper presents the design, fabrication, and experimental characterization of low-loss, G-band (140–220 GHz) H-plane S-bend rectangular waveguides fabricated via a multi-layer stack of laser-micromachined silicon tiles. To overcome sub-millimeter manufacturing challenges, an ultrashort-pulse…

IEEE Transactions on Components, Packaging and Manufacturing Technology, In press. ⟨hal-05782059⟩

• Article dans une revue

Ultralow‐Dispersion Silicon THz Photonic Crystal Interconnects for Multichannel Datalinks

Nikhil Navaratna, Thomas Caiwei Tan, Pascal Szriftgiser, Guillaume Ducournau, Ranjan Singh

All-Silicon (Si) Terahertz (THz) interconnects are a key platform for next-generation on-chip communication, leveraging broadband photonics to connect reconfigurable electronics. Yet their potential remains largely unrealized, due to low reported data rates and a lack of systematic insight into the…

Advanced Materials, 2026, 8 p. ⟨10.1002/adma.74150⟩. ⟨hal-05705648⟩

• Pré-publication, Document de travail

SPARK-IL: Spectral Retrieval-Augmented RAG for Knowledge-driven Deepfake Detection via Incremental Learning

Hessen Bougueffa Eutamene, Abdellah Zakaria Sellam, Abdelmalik Taleb-Ahmed, Abdenour Hadid

Detecting AI-generated images remains a significant challenge because detectors trained on specific generators often fail to generalize to unseen models; however, while pixel-level artifacts vary across models, frequency-domain signatures exhibit greater consistency, providing a promising…

2026. ⟨hal-05596260⟩

• Article dans une revue

Combined Influence of Precursor Source and Solvent Type on Microstructural and Optical Properties of Spin-Coated ZnO Thin Films

Alphonse Déssoudji Gboglo, Mazabalo Baneto, Ognanmi Ako, Abdoul-Razak Ali-Tagba, Bruno Grandidier, Kekeli N’konou

The present work investigates the combined effect of precursor source and solvent on the structural, morphological, and optical properties of ZnO thin films prepared by the spin-coating technique. Three precursor sources (zinc acetate dihydrate, zinc chloride, and zinc nitrate hexahydrate) and four…

Surfaces, 2026, 9 (2), pp.50. ⟨10.3390/surfaces9020050⟩. ⟨hal-05684448⟩

• Article dans une revue

Harnessing normal-shear coupling in metabarriers for deep sub-wavelength underwater noise control

Vinícius F Dal Poggetto, Marco Miniaci

Anthropogenic underwater noise poses a significant threat to marine ecosystems, disrupting key biological functions. Common mitigation strategies include enclosing noise sources within acoustic barriers. Current designs include locally resonant absorbers, which offer narrow-band performance, and…

npj Acoustics, 2026, 2 (1), pp.20. ⟨10.1038/s44384-026-00056-7⟩. ⟨hal-05675214⟩

• Article dans une revue

Real-Time Evolution of the Mechanical Properties of Flax Stems During Post-Harvest Dew Retting: Towards Objective Retting Assessment

Ali Reda, Lionel Buchaillot, Steve Arscott

Post-harvest field dew retting is a critical stage in flax fibre production because it facilitates the separation of fibre bundles from the surrounding stem tissues. In current agricultural practice, the optimum retting stop-point is still assessed largely using empirical criteria, motivating the…

Agriculture, 2026, 16 (18), pp.1940. ⟨10.3390/agriculture16181940⟩. ⟨hal-05742620⟩