The throughput gains of speculative decoding depend on the trade-off between acceptance length and execution latency. We ask when additional acceptance is worth the cost of obtaining it. We establish a comparison protocol spanning training, inference, and evaluation, remeasuring released checkpoints and retraining six...
Yong-Chao Long, Chun-Rui Zheng, Yuxuan Zhou et al.· 0 citations
Conventional sleep staging provides a coarse-grained representation that obscures within-stage depth variation. We developed ECG-SDI, a single-lead electrocardiography (ECG) framework for continuous sleep-depth profiling and digital biomarker extraction. Using 12,392 overnight polysomnographic recordings, we trained an...
Dong-Lin Xie, Qing-Shuo Zhao, Song-Chi Zhou et al.· 0 citations
The proposed NeuroECG model adapts a pretrained ECG foundation model via task-specific fine-tuning and combines the learned deep ECG representation with static clinical covariates to improve prediction in an EEG-free setting.
Jia-Jun Gao, Yi Zhao, Chen-Yang Xu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.