195 citations · 242 across the 18 of their papers we have counts for
19 papers
COMED: The Missing Middle Between Routing and Collaboration in Multi-LLM Inference
Norah Alballa, Wenxuan Zhang, Salma Kharrat +4
No single Large Language Model (LLM) is uniformly reliable across queries, motivating multi-model inference systems that either route among models or combine their outputs. However…
The Boundaries of Automation: A Theory of Persistent Human Participation
Fares Fourati, Hinrich Schütze, Eyke Hüllermeier +1
The rapid progress of AI has intensified the long-standing pursuit of automation: replacing human participation with algorithms wherever possible. Implicit in this pursuit is the a…
Signal from Space: Detecting Schools and Towers to Bridge the Digital Divide
Zakarya Elmimouni, Sandor Farkas, Fares Fourati +3
Reliable internet access is essential for modern education, yet millions of school-aged children especially in developing regions remain offline due to unconnected schools. The Gig…
Label-Efficient School Detection from Aerial Imagery via Weakly Supervised Pretraining and Fine-Tuning
Zakarya Elmimouni, Fares Fourati, Mohamed-Slim Alouini
Accurate school detection is essential for supporting education initiatives, including infrastructure planning and expanding internet connectivity to underserved areas. However, ma…
A Coherence-Based Measure of AGI
Fares Fourati
Recent approaches to evaluating Artificial General Intelligence (AGI) typically summarize a system's capability using the arithmetic mean of its proficiencies across multiple cogni…
ECPv2: Fast, Efficient, and Scalable Global Optimization of Lipschitz Functions
Fares Fourati, Mohamed-Slim Alouini, Vaneet Aggarwal
We propose ECPv2, a scalable and theoretically grounded algorithm for global optimization of Lipschitz-continuous functions with unknown Lipschitz constants. Building on the Every…
Retrieval-Augmented Generation for Reliable Interpretation of Radio Regulations
Zakaria El Kassimi, Fares Fourati, Mohamed-Slim Alouini
We study question answering in the domain of radio regulations, a legally sensitive and high-stakes area. We propose a telecom-specific Retrieval-Augmented Generation (RAG) pipelin…
Every Call is Precious: Global Optimization of Black-Box Functions with Unknown Lipschitz Constants
Fares Fourati, Salma Kharrat, Vaneet Aggarwal +1
Optimizing expensive, non-convex, black-box Lipschitz continuous functions presents significant challenges, particularly when the Lipschitz constant of the underlying function is u…
ACING: Actor-Critic for Instruction Learning in Black-Box LLMs
Salma Kharrat, Fares Fourati, Marco Canini
The effectiveness of Large Language Models (LLMs) in solving tasks depends significantly on the quality of their instructions, which often require substantial human effort to craft…
Stochastic Q-learning for Large Discrete Action Spaces
Fares Fourati, Vaneet Aggarwal, Mohamed-Slim Alouini
In complex environments with large discrete action spaces, effective decision-making is critical in reinforcement learning (RL). Despite the widespread use of value-based RL approa…
Federated Combinatorial Multi-Agent Multi-Armed Bandits
Fares Fourati, Mohamed-Slim Alouini, Vaneet Aggarwal
This paper introduces a federated learning framework tailored for online combinatorial optimization with bandit feedback. In this setting, agents select subsets of arms, observe no…
Addressing Bias Through Ensemble Learning and Regularized Fine-Tuning
Ahmed Radwan, Layan Zaafarani, Jetana Abudawood +2
Addressing biases in AI models is crucial for ensuring fair and accurate predictions. However, obtaining large, unbiased datasets for training can be challenging. This paper propos…
Combinatorial Stochastic-Greedy Bandit
Fares Fourati, Christopher John Quinn, Mohamed-Slim Alouini +1
We propose a novel combinatorial stochastic-greedy bandit (SGB) algorithm for combinatorial multi-armed bandit problems when no extra information other than the joint reward of the…
Randomized Greedy Learning for Non-monotone Stochastic Submodular Maximization Under Full-bandit Feedback
Fares Fourati, Vaneet Aggarwal, Christopher John Quinn +1
We investigate the problem of unconstrained combinatorial multi-armed bandits with full-bandit feedback and stochastic rewards for submodular maximization. Previous works investiga…
FilFL: Client Filtering for Optimized Client Participation in Federated Learning
Fares Fourati, Salma Kharrat, Vaneet Aggarwal +2
Federated learning, an emerging machine learning paradigm, enables clients to collaboratively train a model without exchanging local data. Clients participating in the training pro…
Bridging the Urban-Rural Connectivity Gap through Intelligent Space, Air, and Ground Networks
Fares Fourati, Saeed Hamood Alsamhi, Mohamed-Slim Alouini
Connectivity in rural areas is one of the main challenges of communication networks. To overcome this challenge, a variety of solutions for different situations are required. Optim…
Network Graph Generation through Adaptive Clustering and Infection Dynamics: A Step Towards Global Connectivity
Aniq Ur Rahman, Fares Fourati, Khac-Hoang Ngo +2
More than 40% of the world's population is not connected to the internet, majorly due to the lack of adequate infrastructure. Our work aims to bridge this digital divide by proposi…
Artificial Intelligence for Satellite Communication: A Review
Fares Fourati, Mohamed-Slim Alouini
Satellite communication offers the prospect of service continuity over uncovered and under-covered areas, service ubiquity, and service scalability. However, several challenges mus…
An original framework for Wheat Head Detection using Deep, Semi-supervised and Ensemble Learning within Global Wheat Head Detection (GWHD) Dataset
Fares Fourati, Wided Souidene, Rabah Attia
In this paper, we propose an original object detection methodology applied to Global Wheat Head Detection (GWHD) Dataset. We have been through two major architectures of object det…