Keysight Technologies, Inc. has collaborated with Qualcomm Technologies, Inc. to demonstrate machine learning (ML)-based Channel State Information (CSI) compression to enhance link adaptation efficiency in advanced Multiple-Input Multiple-Output (MIMO) systems at Mobile World Congress (MWC) Barcelona 2026. In a controlled lab validation, the ML-based CSI feedback method achieved more than 40 percent downlink throughput improvement compared to 3GPP eType II CSI reporting in four-layer (rank-4) operation. The demonstration will be featured live at the Keysight booth (Hall 5, #5F41).
As 5G-Advanced networks use more antennas and wider channels, CSI becomes increasingly important in how the network steers beams and selects the right transmission settings. However, sending more detailed CSI can increase uplink reporting overhead, especially for higher-layer MIMO, creating a tradeoff between performance and signaling efficiency.
To address this, Keysight and Qualcomm Technologies tested a mobile test platform powered by a Qualcomm® 5G Modem-RF, together with Keysight’s network emulation solutions in a repeatable lab environment. Under fixed CSI feedback constraints, the ML-based compression method provided a more efficient channel representation than the standardized eType II method while maintaining the information needed for accurate beamforming and link decisions. The result supports scalable advanced MIMO configurations and contributes to industry work exploring AI-native physical-layer enhancements for future 6G wireless systems.
Tingfang Ji, Vice President of Engineering and Head of 6G Research at Qualcomm Technologies, Inc., said: “Efficient CSI feedback is fundamental as antenna dimensions and spatial layers increase. This demonstration shows how Qualcomm’s advanced machine learning algorithms can significantly improve downlink performance over conventional eType II CSI reporting, supporting continued 5G-Advanced innovation and laying the foundation for future AI-native 6G systems.”
Lucas Hansen, Vice President and General Manager, Wireless Test Group, Keysight, said: “AI-native enhancements at the physical layer are essential to scaling next-generation wireless networks. By combining Qualcomm’s modem test platform with our AI-enabled base station emulation solutions, we are enabling rigorous evaluation of ML-based CSI compression and its impact on advanced MIMO performance and 6G research directions.”
Qualcomm branded products are products of Qualcomm Technologies, Inc. and/or its subsidiaries. Qualcomm is a trademark or registered trademark of Qualcomm Incorporated.
Rockwell Automation to Present at the 2026 J.P. Morgan Industrials Conference
03 March 2026
Rockwell Automation, Inc. SVP and CFO, Christian Rothe, and VP, Investor Relations and Market Strategy, Aijana Zellner, will present at the 2026 J.P. Morgan Industrials Conference on Tuesday, March 17, 2026, in Washington, D.C.
The fireside chat will be webcast beginning at approximately 10:50 a.m. EDT and will be available on the Rockwell Automation Investor Relations website at www.rockwellautomation.com/en-us/investors.html.
