Summary

  • Qualcomm and Nokia’s Bell Labs used the Mobile World Congress 2025 to show off an AI-enhanced channel state feedback and how it works with multiple-vendor AI models.
  • The demonstration showed how these can work together in wireless networks to improve flexibility in sequential learning, referred to as sequential learning.
  • This can to facilitate network decoder-first or device encoder-first training, with the two companies designing interoperable AI models without needing to share proprietary details of their implementations.
  • Instead, a training dataset of model input/output pairs is shared from one company to the other to improve network performance.
  • As AI technologies are deployed in real-world networks, it is important to ensure that models work robustly in diverse environments to handle new situations.

By Dean Takahashi

Original Article