Fierce Network Fierce Network Fierce Network
Webinar

AI-Native Mobile RAN Signal Processing - A Transformer-based Approach

ET
60 Minutes

How do you incorporate AI models into real-time mobile network signal processing? SoftBank’s research team has developed an AI-native Air Interface using the Transformer architecture that works in real-world environments. Leveraging this new Transformer AI, this innovation has already delivered a 30% improvement in 5G AI-RAN throughput - setting the stage for the next wave of mobile network advancements.

This technical webinar will showcase the engineering breakthroughs behind SoftBank’s novel unified Transformer architecture - from algorithmic innovations to over-the-air (“OTA”) validation in 3GPP-compliant systems.

Session topics include:

  • Introduction: The problem space description. Why Transformers?
  • Architecture Deep-Dive: Transformer-based unified processing framework design, including components, challenges, design choices and principles. Comparison against other typical machine learning models.
  • Performance Engineering: Real-time deployment strategies and optimization techniques.
  • Use Case Analysis: End-to-end receiver, channel estimation, channel frequency interpolation, and other use cases including SRS prediction.
  • Validation Results: OTA testing data, benchmarks, and performance analysis.
  • Forward Roadmap: Technical pathway towards AI-native design.

Ideal for: Technology leaders and decision-makers at mobile network operators evaluating next-generation solutions; RF, signal processing, and hardware and software engineers at operators and network equipment providers; and AI/ML researchers in telecom.

Don’t miss this opportunity to learn directly from the researchers behind this innovation. Register today!

Speakers

Ryuji Wakikawa

Ryuji Wakikawa

Vice President, Head of Research Institute of Advanced Technology
SoftBank Corp.

Ryuji Wakikawa serves as the Vice President and Head of the Research Institute of Advanced Technology at SoftBank Corp. He is also a Project Professor at the Global Research Institute at Keio University, Japan, where he received his Ph.D. in 2004. Currently, he leads SoftBank’s research institute, where he focuses on the development of advanced technologies, architecture design, and shaping future visions. His work spans areas such as 5G Advanced, 6G, High Altitude Platform Stations (HAPS), Non-Terrestrial Networks (NTN), AI-RAN, quantum technologies, and autonomous driving technologies.

Rajeev Koodli

Rajeev Koodli

Principal Fellow, Research Institute of Advanced Technology
SoftBank Corp.

Dr. Rajeev Koodli is a distinguished global technology leader with over two decades of pioneering work in mobile communications, Internetworking and distributed cloud computing. With his vast expertise in leadership, strategy, architecture, product development, research and innovation, Dr. Koodli has influenced the telecommunications and technology sectors through his transformative contributions to 4G/5G systems, hyperscale cloud infrastructure, IPv6 networking, and AI. His innovations have had significant impact on global mobile networking standards and his technical leadership has contributed to reshaping the industry. He is currently a Principal Fellow at SoftBank Corp.’s Research Institute of Advanced Technology and SVP of AI Infrastructure & Large Telecom Models at SB Telecom America, a subsidiary of SoftBank Corp.

Yuto Kawai

Yuto Kawai

AI Research Engineer, Research Institute of Advanced Technology
SoftBank Corp.

Yuto Kawai is an AI Research Engineer at SoftBank Corp., focusing on AI-for-RAN and the design and prototyping of an AI-native air interface. He develops Transformer-based models for signal processing, emphasizing real-time performance within the latency budgets typical of 3GPP-compliant RANs. Before joining SoftBank, he studied at The University of Tokyo, concentrating on wireless communications and optimization. Combining expertise in AI and wireless, he advances architectures and evaluation toward practical impact—from model design and benchmarking to constraint-aware evaluation for practical adoption.

Roy Chua

Roy Chua

Principal
AvidThink

Roy Chua is a principal at AvidThink, an independent research and advisory service focused on infrastructure technologies. Roy is a frequent speaker at telecom and cloud conferences, and AvidThink has been quoted by and featured in major publications including the WSJ, Fierce Telecom, Fierce Wireless, The New Stack, and Light Reading. Roy was also a co-founder at SDxCentral, a technology publication. He has previously worked as a management consultant for Fortune 500 and startup companies, specializing in go-to-market and product strategy. Roy is a graduate of UC Berkeley's electrical engineering and computer science program and MIT's Sloan School of Business. With over 20 years of experience in telecom and enterprise computing, networking, and security, he has also founded Silicon Valley startups.

Register here!

Already registered? Click here to login.
Date/Time:
ET