Brief

Researchers have developed a new method for learning general-purpose electrophysiological (ExG) signal representations from earphone-based sensors. This approach, called Physiology-informed Multi-band Tokenization (PiMT), breaks down ExG signals into 12 distinct, physiology-informed tokens. The method was tested on a new dataset called DailySense, which covers five human senses, and demonstrated superior performance on various tasks compared to existing state-of-the-art techniques. AI

Researchers have developed ConSensus, a novel multi-agent framework designed to improve multimodal sensing by breaking down tasks for specialized, modality-aware agents. This approach uses a hybrid fusion mechanism that combines semantic aggregation for cross-modal reasoning with statistical consensus for robustness against noise and missing data. Evaluations on five benchmarks showed ConSensus achieved a 7.1% average accuracy improvement over single-agent methods and significantly reduced fusion token costs. AI