Buy your pass
OnlineDiscovery - AI/ML in 5G Badge available

Wireless foundation model (WiFo) empowered SoM system design

  • Register

    Watch

    Watch and get your discovery badge

    * Register (or log in) to the Neural Network to add this session to your agenda or watch the replay

    • Date
    26 November 2025
    Timeframe
    12:00 - 13:00 CET Geneva
    Duration
    60 minutes

    To support future intelligent multifunctional 6G wireless communication networks, Synesthesia of Machines (SoM) is proposed as a novel paradigm for AI-native task-oriented intelligent multi-modal sensing–communication integration. However, existing SoM system designs rely on task-specific AI models and face challenges such as insufficient performance, limited generalization, and fragmented design. Recently, foundation models have ushered in a paradigm shift in AI design, achieving landmark successes, such as ChatGPT, in NLP and beyond. Their strong reasoning and generalization capabilities open new opportunities to address the aforementioned challenges. Therefore, we present WiFo, the first wireless foundation model for channel prediction, which demonstrates strong channel prediction in both the time and frequency domains and zero-shot generalization across diverse systems and datasets. Nevertheless, as a universal CSI representation model, its performance on downstream wireless-related tasks remains to be fully explored.

    In this challenge, we aim to encourage participants to fully unlock WiFo’s potential on wireless downstream tasks. Competitors will fine-tune the pretrained WiFo to power three tasks: channel estimation, LoS/NLoS classification, and vision-aided wireless localization. For each task, we provide carefully curated datasets and ready-to-run baselines to keep the entry barrier low. Scoring will consider both task performance and the model’s parameter count to incentivize efficient designs. The total prize pool is CHF 4,000 (≈ CNY 35,000), with a first prize of CNY 20,000.

     

    Session Objectives:

    By the end of this session, participants will be able to:

    • Introduce the concept of SoM.
    • Present the WiFo model and its applications to wireless downstream tasks.
    • Introduce the three downstream tasks for this challenge.
    • Explain the provided baselines, scoring rules, and results submission workflow.
    • Address additional competition-related Q&A.

     

    Recommended Mastery Level / Prerequisites:

    • Basic understanding of the wireless communication domain.
    • Basic knowledge of deep learning and the ability to train neural networks
    View presentation
    • Discovery badge available
    Showcase it on your LinkedIn profile or your professional portfolio
    Verified badge is available for CHF 10
    Learn more
    Share this session with your network
    Discover more from programme stream
    Discovery - AI/ML in 5G
    Estimation of site-specific radio propagation loss with minimal information

    Estimation of site-specific radio propagation loss with minimal information

    15 December 2025 - 09:00 to 10:00

    Related stories

    Are you sure you want to remove this speaker?