2 citations · 4 across the 7 of their papers we have counts for
7 papers
Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling
Falcon LLM Team, Iheb Chaabane, Puneesh Khanna +8
This work introduces Falcon-H1R, a 7B-parameter reasoning-optimized model that establishes the feasibility of achieving competitive reasoning performance with small language models…
Alignment with Preference Optimization Is All You Need for LLM Safety
Reda Alami, Ali Khalifa Almansoori, Ahmed Alzubaidi +3
We demonstrate that preference optimization methods can effectively enhance LLM safety. Applying various alignment techniques to the Falcon 11B model using safety datasets, we achi…
On the Accuracy of Hotelling-Type Asymmetric Tensor Deflation: A Random Tensor Analysis
Mohamed El Amine Seddik, Maxime Guillaud, Alexis Decurninge +1
This work introduces an asymptotic study of Hotelling-type tensor deflation in the presence of noise, in the regime of large tensor dimensions. Specifically, we consider a low-rank…
Optimizing Orthogonalized Tensor Deflation via Random Tensor Theory
Mohamed El Amine Seddik, Mohammed Mahfoud, Merouane Debbah
This paper tackles the problem of recovering a low-rank signal tensor with possibly correlated components from a random noisy tensor, or so-called spiked tensor model. When the und…
When Random Tensors meet Random Matrices
Mohamed El Amine Seddik, Maxime Guillaud, Romain Couillet
Relying on random matrix theory (RMT), this paper studies asymmetric order- spiked tensor models with Gaussian noise. Using the variational definition of the singular vectors an…
Node Feature Kernels Increase Graph Convolutional Network Robustness
Mohamed El Amine Seddik, Changmin Wu, Johannes F. Lutzeyer +1
The robustness of the much-used Graph Convolutional Networks (GCNs) to perturbations of their input is becoming a topic of increasing importance. In this paper, the random GCN is i…
Deep Multi-class Adversarial Specularity Removal
John Lin, Mohamed El Amine Seddik, Mohamed Tamaazousti +2
We propose a novel learning approach, in the form of a fully-convolutional neural network (CNN), which automatically and consistently removes specular highlights from a single imag…