2 citations · 2 across the 4 of their papers we have counts for
9 papers
ML in a Box: Analyzing Containerization Practices in Open Source ML Projects
Faten Jebari, Emna Ksontini, Amine Barrak +1
Containerization has become increasingly essential in the machine learning (ML) domain, providing reproducibility, portability, and environment consistency. While prior studies hav…
A Large-Scale Dataset of MCP Implementations on GitHub
Benny Toeppe, Amine Barrak, Emna Ksontini
The rapid emergence of the Model Context Protocol (MCP) has introduced a new standard for connecting large language models to external tools and services. Despite its rapid adoptio…
Shard the Gradient, Scale the Model: Serverless Federated Aggregation via Gradient Partitioning
Amine Barrak
Federated learning (FL) aggregation on serverless platforms faces a hard scalability ceiling: existing architectures (lambda-FL, LIFL) partition clients across aggregators, but eve…
From REST to MCP: An Empirical Study of API Wrapping and Automated Server Generation for LLM Agents
Meriem Mastouri, Emna Ksontini, Amine Barrak +1
The Model Context Protocol (MCP) is emerging as a standard interface through which LLM agents invoke external tools, and a growing ecosystem of MCP servers now mediates access to v…
Traceability and Accountability in Role-Specialized Multi-Agent LLM Pipelines
Amine Barrak
Sequential multi-agent systems built with large language models (LLMs) can automate complex software tasks, but they are hard to trust because errors quietly pass from one stage to…
Cost-Performance Analysis: A Comparative Study of CPU-Based Serverless and GPU-Based Training Architectures
Amine Barrak, Fabio Petrillo, Fehmi Jaafar
The field of distributed machine learning (ML) faces increasing demands for scalable and cost-effective training solutions, particularly in the context of large, complex models. Se…