1 citations · 1 across the 14 of their papers we have counts for
14 papers
Adaptive Head Budgeting for Efficient Multi-Head Attention
Bilal Faye, Abdoulaye Mbaye, Hanane Azzag +1
Multi-head attention enables Transformers to capture diverse representations, but all attention heads are typically activated for every input, regardless of task complexity. For co…
Energy-Regularized Spatial Masking: A Novel Approach to Enhancing Robustness and Interpretability in Vision Models
Tom Devynck, Bilal Faye, Djamel Bouchaffra +3
Deep convolutional neural networks achieve remarkable performance by exhaustively processing dense spatial feature maps, yet this brute-force strategy introduces significant comput…
NeuroGame Transformer: Gibbs-Inspired Attention Driven by Game Theory and Statistical Physics
Djamel Bouchaffra, Faycal Ykhlef, Hanene Azzag +2
Standard attention mechanisms in transformers are limited by their pairwise formulation, which hinders the modeling of higher-order dependencies among tokens. We introduce the Neur…
Prototype-Guided Diffusion: Visual Conditioning without External Memory
Bilal Faye, Hanane Azzag, Mustapha Lebbah
Diffusion models achieve state-of-the-art image generation but remain computationally costly due to iterative denoising. Latent-space models like Stable Diffusion reduce overhead y…
Value-Free Policy Optimization via Reward Partitioning
Bilal Faye, Hanane Azzag, Mustapha Lebbah
Single-trajectory preference optimization methods learn from datasets of ((prompt, response, reward)) tuples, offering a practical alternative to pairwise preference learning by di…
Game Theory Meets Statistical Mechanics in Deep Learning Design
Djamel Bouchaffra, Fayçal Ykhlef, Bilal Faye +2
We present a novel deep graphical representation that seamlessly merges principles of game theory with laws of statistical mechanics. It performs feature extraction, dimensionality…
OneEncoder: A Lightweight Framework for Progressive Alignment of Modalities
Bilal Faye, Hanane Azzag, Mustapha Lebbah
Cross-modal alignment Learning integrates information from different modalities like text, image, audio and video to create unified models. This approach develops shared representa…
Adaptative Context Normalization: A Boost for Deep Learning in Image Processing
Bilal Faye, Hanane Azzag, Mustapha Lebbah +1
Deep Neural network learning for image processing faces major challenges related to changes in distribution across layers, which disrupt model convergence and performance. Activati…
Unsupervised Adaptive Normalization
Bilal Faye, Hanane Azzag, Mustapha Lebbah +1
Deep neural networks have become a staple in solving intricate problems, proving their mettle in a wide array of applications. However, their training process is often hampered by…
Lightweight Modular Parameter-Efficient Tuning for Open-Vocabulary Object Detection
Bilal Faye, Hanane Azzag, Mustapha Lebbah
Open-vocabulary object detection (OVD) extends recognition beyond fixed taxonomies by aligning visual and textual features, as in MDETR, GLIP, or RegionCLIP. While effective, these…
Supervised Batch Normalization
Bilal Faye, Mustapha Lebbah, Hanane Azzag
Batch Normalization (BN), a widely-used technique in neural networks, enhances generalization and expedites training by normalizing each mini-batch to the same mean and variance. H…
Enhancing Neural Network Representations with Prior Knowledge-Based Normalization
Bilal Faye, Hanane Azzag, Mustapha Lebbah +1
Deep learning models face persistent challenges in training, particularly due to internal covariate shift and label shift. While single-mode normalization methods like Batch Normal…
Lightweight Cross-Modal Representation Learning
Bilal Faye, Hanane Azzag, Mustapha Lebbah +1
Low-cost cross-modal representation learning is crucial for deriving semantic representations across diverse modalities such as text, audio, images, and video. Traditional approach…
Context Normalization Layer with Applications
Bilal Faye, Mohamed-Djallel Dilmi, Hanane Azzag +2
Normalization is a pre-processing step that converts the data into a more usable representation. As part of the deep neural networks (DNNs), the batch normalization (BN) technique…