The field of terahertz communications and 6G networks is moving towards more efficient and scalable solutions. Researchers are exploring the use of deep learning frameworks to predict channel impulse responses and beam coherence times, which is essential for reliable and high-speed communication. The impact of antenna arrays misalignment on near-field distance calculations is also being investigated, providing essential guidelines for optimizing system deployment in realistic scenarios. Furthermore, hybrid neural network models are being developed for indoor localization and navigation in complex environments. Noteworthy papers include:

• A deep learning framework that predicts 7 GHz channel impulse responses by leveraging abundant 3.5 GHz CIRs, achieving a median gain error of 0.58 dB and a phase prediction error of 0.27 rad.
• A study that analyzes the impact of spatial misalignment on near-field distance calculations in THz systems, deriving exact analytical expressions and simplified approximations for the near-field boundary.