From Large Language Models to Large Perceptive Models: AI That Understands the Physical World
Title: From Large Language Models to Large Perceptive Models: AI That Understands the Physical World
Date: 13th Oct 2026 (Tuesday)
Time: 0930 – 1130 am
Venue: EEE Executive Seminar Rm (S2.2-B2-53)
Abstract:
Large Language Models have demonstrated that sufficiently large models trained on massive corpora can acquire remarkable capabilities for understanding, reasoning, and generation. Yet language represents only a small fraction of the information generated by the physical world. Future intelligent systems will increasingly need to understand not only text, but also radio signals, images, video, radar, LiDAR, acoustic signals, wireless channels, and other sensory modalities. This talk introduces the concept of Large Perceptive Models (LPMs): foundation models designed to learn general-purpose representations of the physical world from heterogeneous sensing data. Rather than developing a separate AI model for every sensor, environment, and task, LPMs aim to learn transferable representations that can support perception, localization, sensing, prediction, communication, and decision-making across multiple domains. Particular attention will be given to wireless and RF signals, where the environment itself becomes a source of information about objects, people, mobility, materials, and electromagnetic propagation.
Speaker: Prof. Merouane Debbah, Senior Director, Digital Future Institute, Khalifa University, Abu Dhabi
Bio: Merouane Debbah is a researcher, educator and technology entrepreneur. Over his career, he has founded several public and industrial research centers, start-ups and is now Professor at Khalifa University of Science and Technology in Abu Dhabi and founding Senior Director of KU Digital Future Institute. He is a frequent keynote speaker at international events in the field of telecommunication and AI. His research has been lying at the interface of fundamental mathematics, algorithms, statistics, information and communication sciences with a special focus on random matrix theory and learning algorithms. In the Communication field, he has been at the heart of the development of small cells (4G), Massive MIMO (5G) and Large Intelligent Surfaces (6G) technologies. In the AI field, he is known for his work on Large Language Models, distributed AI systems for networks and semantic communications. He received multiple prestigious distinctions, prizes and best paper awards (more than 50 IEEE best paper awards) for his contributions to both fields and according to research.com is ranked as the best scientist in France in the field of Electronics and Electrical Engineering. He is an IEEE Fellow, a WWRF Fellow, a Eurasip Fellow, an AAIA Fellow, an Institut Louis Bachelier Fellow, an AIIA Fellow and a Membre émérite SEE. More recently, his work has focused on the convergence of generative AI and telecommunications. He has contributed to the development of domain-specific foundation models for networks, including TelecomGPT, a family of large language models designed to understand and reason about telecommunications problems. His research also explores agentic AI and multi-agent systems for autonomous networks, RF foundation models, Large Perceptive Models, telecom world models, semantic communications, and the use of generative AI for sensing, network operation, optimization, and reasoning over the physical world. He is actually chair of the IEEE Large Generative AI Models in Telecom (GenAINet) Emerging Technology Initiative and a member of the Marconi Prize Selection Advisory Committee.
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
- EEE Executive Seminar Rm (S2.2-B2-53)
- Singapore, Singapore
- Singapore