Tag
This paper proposes a domain knowledge-based temporal-spatial graph convolution network for ECG recognition that uses PRQST landmarks and double-stream directed graphs to model intra- and inter-cycle dependencies, achieving state-of-the-art F1 scores on the First Chinese ECG Intelligent Competition dataset.
This paper introduces Temporal-Spatial Parallel Decoding (TSPD) and Confidence Extrapolation (CE) to accelerate inference in diffusion-based large language models by dynamically deciding when tokens have converged and forecasting logit trends, reducing unnecessary denoising steps while preserving output quality.