Yonsei-RAMO-Yberg is integrating our AI-Native GPU vRAN on an NVIDIA DGX Spark running NVIDIA Aerial, using an iPhone and K-pop streaming as the application workload. Our campus testbed operates in the 4.7 GHz private 5G band (n79) with a 100 MHz channel bandwidth, both indoor and outdoor O-RU deployment environments. Technical details and evaluation results will be presented in upcoming technical reports, conference presentations, and publications later this year, including

E2E AI-Native GPU RAN Testing with iPhone At Yonsei University, we are evaluating OCUDU with a CUDA-accelerated Layer 1 (L1) running on the NVIDIA DGX platform. In addition, we have conducted integration and interoperability testing using commercial O-RUs, UEs, and Keysight RuSIM on NVIDIA GPU platforms with an OAI-based vRAN CU/DU integrated with NVIDIA Aerial. Our evaluation focuses on two primary objectives. First, we are assessing the variations in CPU utilization enabled

At MWC 2026 (Barcelona, Spain), Yonsei-RAMO-Yberg (led by Prof. Seong-Lyun Kim) demonstrated cutting-edge next-generation network technologies developed under the support of the Ministry of Science and ICT. Key Highlights: LLM-based Antenna Management: In collaboration with SUTD (Singapore) and Viavi, the lab demonstrated technology where AI autonomously judges real-time situations to efficiently control antennas. Performance: By applying LLM technology (typically used in mod

We are so happy to share our (Yberg/Yonsei) private 5G experiences (smart factory) at MWC2025, jointly with LiteON, also to have a...

We are so happy to share our (Yberg/Yonsei) private 5G experiences (smart factory) at MWC2025, jointly with LiteON, and Cumucore.

We have entered into a business agreement with our long-time research partner, Cumucore, a Finnish company. Cumucore was founded from...