This talk explores the transformative role of AI/ML in advancing radio hardware design, particularly for next-generation base-station systems. It highlights the advantages of AI in automating and optimizing design workflows—enhancing efficiency, precision, and adaptability in complex RF environments.

The session introduces a visionary approach: combining generative AI, large language models, and human-in-the-loop methodologies to reimagine the architectural foundations of base-station radio systems. This fusion opens the door to novel design paradigms that go beyond conventional engineering constraints.

Using the framework of AI/ML Ambition Levels—from Level 1 (Design Automation) to Level 3 (Design Innovation)—the talk evaluates current capabilities, asserting that Levels 1 and 2 are already attainable in specific domains such as antenna design and signal chain optimization. Achieving Level 3, however, demands breakthroughs in reasoning-aware AI, cross-domain learning, and scalable simulation environments.

Key challenges and opportunities are discussed including the need for richer datasets, interpretable models, and real-time co-design tools that bridge the gap between AI and hardware engineering—paving the way for intelligent, adaptive, and innovative radio systems.

Featured Speakers:  John Cioffi, Reinaldo Valenzuela, Gerhard Fettweis, Rahim Tafazolli, Khaled Letaief, Chengshan Xiao, Alberto Leon-Garcia, Sherman Shen, Wen Tong, Peiying Zhu, Wei Zhang, Kostas Plataniotis

As 6G networks evolve to tightly integrate AI with communication infrastructure, the critical design challenges and trade-offs in deploying intelligent services at the edge must be explored. In this talk, the featured experts discuss how to balance high-performance AI with the limited computational, memory, and energy resources of edge devices—without compromising real-time responsiveness in latency-sensitive applications.  They delve into the architectural dilemma: should 6G systems be primarily shaped by the computational demands of distributed learning and inference, or by communication constraints like bandwidth and latency? Through this lens, the speakers unpack the fundamental trade-offs between processing, transmission, and intelligence distribution.  

Emerging strategies for on-device model adaptation, enabling edge devices to learn and evolve over time without relying on cloud-based retraining are explored. Techniques such as federated learning, continual learning, and lightweight model updates are discussed, along with the challenges of maintaining accuracy, privacy, and efficiency in dynamic environments.

Featured Speakers:  John Cioffi, Reinaldo Valenzuela, Gerhard Fettweis, Rahim Tafazolli, Khaled Letaief, Chengshan Xiao, Alberto Leon-Garcia, Sherman Shen, Wen Tong, Peiying Zhu, Wei Zhang, Kostas Plataniotis

As wireless environments grow increasingly dynamic and complex, traditional signal processing methods are reaching their limits. In this session, experts explore the urgent need for smarter wireless signal processing, emphasizing the limitations of conventional neural networks, which—while effective at detection and estimation—struggle with generalization, interpretability, and adaptability.  Reasoning-Enhanced Neural Networks, a new paradigm that fuses deep learning with reasoning capabilities, is explored as well as hybrid models that can capture causal relationships, enforce logical constraints, and adapt to dynamic environments, enabling a shift from reactive to proactive signal processing.  

Featured speakers discuss cutting-edge reasoning techniques—such as graph neural networks (GNNs) for relational reasoning, reinforcement learning (RL) for temporal reasoning, neural-symbolic systems for logical reasoning, and Bayesian neural networks (BNNs) for probabilistic reasoning. Despite their promise, these approaches face significant challenges, including the lack of large-scale reasoning-labeled datasets, high computational costs, and integration hurdles with real-time systems.

Ultimately, the session makes a compelling case for evolving from mere learning to true understanding in wireless signal processing—paving the way for more robust, interpretable, and intelligent communication systems.

Featured Speakers:  John Cioffi, Reinaldo Valenzuela, Gerhard Fettweis, Rahim Tafazolli, Khaled Letaief, Chengshan Xiao, Alberto Leon-Garcia, Sherman Shen, Wen Tong, Peiying Zhu, Wei Zhang, Kostas Plataniotis

Speakers discuss the transformative potential of artificial intelligence in modern network infrastructures, examining how AI can dynamically automate workflows among network entities, enabling seamless execution of complex services through adaptive orchestration and intelligent decision-making. Real-time optimization is discussed, highlighting how AI can leverage continuous feedback—such as Quality of Service (QoS) metrics—to fine-tune network performance and ensure reliability and efficiency.  Beyond traditional roles, speakers explore the evolving function of networks as active participants in AI ecosystems. Networks are no longer just conduits for data; they can now host AI models, facilitate distributed learning, and provide context-aware services. The interplay between AI embedded in network infrastructure and AI at the application layer is discussed, as well as how collaborative AI agents and shared intelligence, networks and applications can co-evolve, enabling smarter, more responsive digital environments.

Featured Speakers:  John Cioffi, Reinaldo Valenzuela, Gerhard Fettweis, Rahim Tafazolli, Khaled Letaief, Chengshan Xiao, Alberto Leon-Garcia, Sherman Shen, Wen Tong, Peiying Zhu, Wei Zhang, Kostas Plataniotis

In this talk, the speakers discuss the transformative potential of AI-driven, fully adaptive physical layer design in wireless communications, exploring whether AI can replace traditional architectures by learning and generalizing across highly dynamic RF environments. Key challenges such as ensuring reliability, managing computational complexity, and curating high-quality training data are highlighted, especially in the context of AI-integrated antenna arrays. Speakers also look ahead to the next five years, examining how generative AI and quantum computing may revolutionize antenna design and signal processing, paving the way for a truly intelligent and resilient 6G physical layer.

Featured Speakers:  John Cioffi, Reinaldo Valenzuela, Gerhard Fettweis, Rahim Tafazolli, Khaled Letaief, Chengshan Xiao, Alberto Leon-Garcia, Sherman Shen, Wen Tong, Peiying Zhu, Wei Zhang, Kostas Plataniotis

This talk explores the transformative potential of 6G Radio Access Networks (RAN) through the convergence of novel waveforms, advanced signal processing, and intelligent resource allocation. The speakers discuss how integrated communication, sensing, and AI can unlock groundbreaking services—from hyper-precise localization to immersive XR and autonomous systems—while meeting stringent KPIs like ultra-low latency and energy efficiency. The talk also addresses the role of AI/ML in dynamically optimizing RAN performance across communication, sensing, and computation layers. The critical challenge of acquiring and sharing high-quality training data in real-world wireless environments to accelerate innovation across academia and industry is also discussed.  

Featured Speakers:  John Cioffi, Reinaldo Valenzuela, Gerhard Fettweis, Rahim Tafazolli, Khaled Letaief, Chengshan Xiao, Alberto Leon-Garcia, Sherman Shen, Wen Tong, Peiying Zhu, Wei Zhang, Kostas Plataniotis