5 papers
Martingale Foresight Sampling: A Principled Approach to Inference-Time LLM Decoding
Huayu Li, ZhengXiao He, Siyuan Tian +2
Standard autoregressive decoding in large language models (LLMs) is inherently short-sighted, often failing to find globally optimal reasoning paths due to its token-by-token gener…
Advancing time series completion via RFAMoE and MDFF
Ci Zhang, Huayu Li, Changdi Yang +6
Recent studies show that using diffusion models for time series signal reconstruction holds great promise. However, such approaches remain largely unexplored in the domain of medic…
NeuroHD-RA: Neural-distilled Hyperdimensional Model with Rhythm Alignment
ZhengXiao He, Jinghao Wen, Huayu Li +2
We present a novel and interpretable framework for electrocardiogram (ECG)-based disease detection that combines hyperdimensional computing (HDC) with learnable neural encoding. Un…
Multimodal Cardiovascular Risk Profiling Using Self-Supervised Learning of Polysomnography
Zhengxiao He, Huayu Li, Geng Yuan +4
Methods: We developed a self-supervised deep learning model that extracts meaningful patterns from multi-modal signals (Electroencephalography (EEG), Electrocardiography (ECG), and…
Smarter Together: Combining Large Language Models and Small Models for Physiological Signals Visual Inspection
Huayu Li, Zhengxiao He, Xiwen Chen +8
Large language models (LLMs) have shown promising capabilities in visually interpreting medical time-series data. However, their general-purpose design can limit domain-specific pr…