Cédric Adjih — accepted AI-conference papers

2026

NetDiff: Graph Diffusion with Improved Global Capabilities to Generate and Update Mobile Network Topologies

Félix Marcoccia, Cédric Adjih, Victor Fagoo, Paul Mühlethaler, Thomas Watteyne, Gilles de Saint Julien

ICML 2026poster

We introduce NetDiff, a node-conditioned denoising diffusion model that generates directional link topologies and a two-slot transmit/receive parity for mobile ad hoc networks. Directional antennas can yield high throughput but require globally consistent link decisions under sector, interference, c…

Cited by 0 Source ↗Scholar ↗

2018

Hand: Header-Assisted Network Decoding

Qiuyi Wang, Yang Xiao, Michel Kieffer, Cédric Adjih

ICASSP 2018accepted

This paper considers the problem of data collection in a sensor network using network coding (NC). It proposes a decoding approach, called HAND, which does not require source packets to be supplemented with NC headers (with encoding vectors), classically used to decode the network-coded packets. HAN…

Cited by 0 Source ↗Scholar ↗