Novel Techniques for Low-latency, Spectrally Efficient, and Energy-lean Channel Estimation and Transceiver Adaptation in Challenging Environments

Scope of the papers

This Special Session highlights novel research on channel estimation and transceiver adaptation in highly dynamic, noisy propagation environments — a long-standing challenge now made urgent by the demands of smart manufacturing and intelligent spaces. Generative AI offers a promising path forward, but brings its own requirements: large and diverse datasets for training and inference, multimodal sensing and solutions to data fusion, synchronization, and computational cost. This Special Session aims to provide a technical forum to address AI-based and other novel approaches to ultra-low-latency, spectrally efficient, and energy-lean channel estimation for advanced manufacturing (AM) and other environments of similar dynamics (further addressed as AM).

We invite submissions in the form of original research papers presenting novel approaches to modeling radio propagation and ultralow-latency estimation of wireless channels. We welcome papers at the intersection of GenAI, state-of-the-art simulators, digital twins with augmented and virtual reality and highly integrated and orchestrated sensor systems that provide radio scene assessment. Contributions on transceiver adaptation, and those proposing new evaluation frameworks for approaches and systems designed to overcome the latency and flexibility barriers in wireless communications for AM are also welcome.

Topics of interest include, but are not limited to:

• Integrated Sensing and Communications for Advanced Manufacturing (AM)
• Information-theoretic treatment of multimodal GenAI for propagation modeling
• AI-driven orchestration and coordination of sensors for radio scene assessment in the AM
• Generative models for radio propagation modeling in the AM
• Generative models for beam forming and beam steering
• Integration of AI and state-of-the-art simulators for ultralow-latency radio propagation modeling
• Physics-based AI for ultralow-latency radio propagation modeling
• Multimodal data for radio propagation modeling
• Sustainability and energy-aware radio propagation modeling in dynamic and harsh environments
• Radio propagation modeling for intelligent digital twins in advanced manufacturing
• Security, Privacy, and Trust in radio propagation models for advanced manufacturing
• Evaluation frameworks for radio propagation modeling in the AM
• Channel Estimation for Reconfigurable Intelligent Surfaces
• Beamforming and Optimization of Reconfigurable Intelligent Surfaces