collaborators

6 papers

cs.AI2026

S-SPPO: Semantic-Calibrated Self-Play Preference Optimization

Xiwen Chen, Wenhui Zhu, Jingjing Wang +13

Aligning Large Language Models (LLMs) with human preferences is often formulated via Direct Preference Optimization (DPO). However, the standard Bradley-Terry instantiation of DPO…

cs.LG2026

Learning Fingerprints for Medical Time Series with Redundancy-Constrained Information Maximization

Huayu Li, ZhengXiao He, Xiwen Chen +4

Learning meaningful representations from medical time series (MedTS) such as ECG or EEG signals is a critical challenge. These signals are often high-dimensional, variable-length a…

cs.LG2026

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…

eess.SP2025

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…

cs.LG2025

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…

cs.AI2025

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…