The field of signal processing and machine learning is moving towards the development of more efficient and effective algorithms for handling complex data. Researchers are exploring new techniques for sparse coding, graph-based methods, and sequential regression, with a focus on improving accuracy and reducing computational complexity. One notable trend is the integration of multiple technologies and modalities to enhance performance and coverage. Noteworthy papers include:

• A low-rank coding model for 2-dictionary scenarios that achieves up to 90% sparser solutions compared to non-low-rank and analytical dictionary baselines.
• A Soft Graph Transformer for MIMO detection that closely approaches Maximum Likelihood performance and surpasses prior Transformer-based approaches.
• A MultiEncoder Fusion-Attention Wave Network for integrated sensing and communication indoor scene inference that achieves high accuracy by fusing information from multiple technologies.