Category: News
-
MCP Enablement PI1
Date
Formats
Categories
- News
MCP Enablement PI1 is a server, which implements the MCP protocol, designed to expose Orange’s network APIs, as tools directly usable by AI assistants. It… -
goodkit
Date
Formats
Categories
- News
Current tools for monitoring virtual machines in the cloud either severely degrade the service being inspected, or rely on in-guest agents, that an attacker could… -
Evaluation of RAG Metrics in an Application Context
Date
Formats
Categories
- News
Nowadays, the evaluation of RAG (Retrieval Augmented Generation) systems relies heavily on LLM-as-a-judge metrics. However, the reliability of these metrics varies depending on the application… -
SSAD
Date
Formats
Categories
- News
The Self-Supervised Anomaly Detection (SSAD) library is a Python framework dedicated to self-supervised training of autoencoder-based reconstruction models for anomaly detection. It formalizes and industrializes… -
Factual Knowledge Assessment of Language Models Using Distractors
Date
Formats
Categories
- News
Language models encode extensive factual knowledge within their parameters. The accurate assessment of this knowledge is crucial for understanding and improving these models. In the… -
Symbal-Latin
Date
Formats
Categories
- News
The Symbal-Latin engine is a generic symbol and graphic gesture recognition technology (letters, symbols, command gestures) developed by Orange Research. It is based on a… -
Attentionless Streaming ASR
Date
Formats
Categories
- News
attentionless-streaming-asr contains the codebase associated with the paper Do we really need Self-Attention for Streaming Automatic Speech Recognition?, which investigates the role of self-attention mechanisms… -
ib-ORAN
Date
Formats
Categories
- News
ns3-iboran is an ns-3 module for intent based Open Radio Access Network (Open RAN). ns3-iboran provides a comprehensive tool to design and simulate intent-driven Radio… -
MMD-SCD
Date
Formats
Categories
- News
This project is part of a CIFRE PhD thesis aimed at developing anomaly detection algorithms for time series. The repository contains the implementation and comparison… -
Learning High-Dimensional Parity Functions with Product Networks using Gradient Descent
Date
Formats
Categories
- News
This research project, conducted jointly by Orange Research and Télécom Paris, addresses a fundamental challenge in machine learning: learning parity (XOR) functions in high-dimensional spaces…