papers

Publications (28)

cs.CV2024

Enhancing Vision-Language Models Generalization via Diversity-Driven Novel Feature Synthesis

Siyuan Yan, Cheng Luo, Zhen Yu +1

Vision-language foundation models like CLIP have shown impressive zero-shot generalization, but finetuning on downstream datasets can cause overfitting and loss of its generalizati…

cs.LG2024

Adaptive Transformer Modelling of Density Function for Nonparametric Survival Analysis

Xin Zhang, Deval Mehta, Yanan Hu +8

Survival analysis holds a crucial role across diverse disciplines, such as economics, engineering and healthcare. It empowers researchers to analyze both time-invariant and time-va…

cond-mat.mes-hall2004

Quantitative Theory of Nanowire and Nanotube Antenna Performance

Peter J. Burke, Shengdong Li, Zhen Yu

We present quantitative predictions of the performance of nanotubes and nanowires as antennas, including the radiation resistance, the input reactance and resistance, and antenna e…

cs.LG2026

MambaLSTM: A Spatio-Temporal Framework for Enhanced Traffic Accident Risk Prediction

Zhen Yu, Yachao Yuan, Zixiang Peng +2

In traffic accident risk prediction, most studies overlook the extra noise that could be incorporated when fusing temporal features into spatial features, and some models struggle…

cs.CV2020

Melanoma Diagnosis with Spatio-Temporal Feature Learning on Sequential Dermoscopic Images

Zhen Yu, Jennifer Nguyen, Xiaojun Chang +5

Existing studies for automated melanoma diagnosis are based on single-time point images of lesions. However, melanocytic lesions de facto are progressively evolving and, moreover,…

cs.CL2022

TextHacker: Learning based Hybrid Local Search Algorithm for Text Hard-label Adversarial Attack

Zhen Yu, Xiaosen Wang, Wanxiang Che +1

Existing textual adversarial attacks usually utilize the gradient or prediction confidence to generate adversarial examples, making it hard to be deployed in real-world application…

cs.CV2024

Progressive trajectory matching for medical dataset distillation

Zhen Yu, Yang Liu, Qingchao Chen

It is essential but challenging to share medical image datasets due to privacy issues, which prohibit building foundation models and knowledge transfer. In this paper, we propose a…

cs.CV2025

A Multimodal Vision Foundation Model for Clinical Dermatology

Siyuan Yan, Zhen Yu, Clare Primiero +22

Diagnosing and treating skin diseases require advanced visual skills across domains and the ability to synthesize information from multiple imaging modalities. While current deep l…

cs.LG2025

scDD: Latent Codes Based scRNA-seq Dataset Distillation with Foundation Model Knowledge

Zhen Yu, Jianan Han, Yang Liu +1

Single-cell RNA sequencing (scRNA-seq) technology has profiled hundreds of millions of human cells across organs, diseases, development and perturbations to date. However, the high…

cs.CV2024

Universal Semi-Supervised Learning for Medical Image Classification

Lie Ju, Yicheng Wu, Wei Feng +4

Semi-supervised learning (SSL) has attracted much attention since it reduces the expensive costs of collecting adequate well-labeled training data, especially for deep learning met…

eess.IV2021

Early Melanoma Diagnosis with Sequential Dermoscopic Images

Zhen Yu, Jennifer Nguyen, Toan D Nguyen +6

Dermatologists often diagnose or rule out early melanoma by evaluating the follow-up dermoscopic images of skin lesions. However, existing algorithms for early melanoma diagnosis a…

eess.IV2024

Prompt-driven Latent Domain Generalization for Medical Image Classification

Siyuan Yan, Chi Liu, Zhen Yu +7

Deep learning models for medical image analysis easily suffer from distribution shifts caused by dataset artifacts bias, camera variations, differences in the imaging station, etc.…

cs.CV2023

Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision

Siyuan Yan, Zhen Yu, Xuelin Zhang +5

Deep neural networks have demonstrated promising performance on image recognition tasks. However, they may heavily rely on confounding factors, using irrelevant artifacts or bias w…

cs.CV2023

EPVT: Environment-aware Prompt Vision Transformer for Domain Generalization in Skin Lesion Recognition

Siyuan Yan, Chi Liu, Zhen Yu +6

Skin lesion recognition using deep learning has made remarkable progress, and there is an increasing need for deploying these systems in real-world scenarios. However, recent resea…

cs.CV2020

CNN in CT Image Segmentation: Beyound Loss Function for Expoliting Ground Truth Images

Youyi Song, Zhen Yu, Teng Zhou +4

Exploiting more information from ground truth (GT) images now is a new research direction for further improving CNN's performance in CT image segmentation. Previous methods focus o…

cond-mat.str-el2025

Magnetism and Correlated Electrons in LaCrGeN

Jiao-Jiao Meng, Yu-Sen Xiao, Gen Li +22

We report the synthesis, structure and physical properties of a new quaternary nitride LaCrGeN. The compound crystallizes in the CeCrSiC-type structure (P4/mmm), fe…

cs.CV2025

MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment

Siyuan Yan, Xieji Li, Ming Hu +3

Dermatological diagnosis represents a complex multimodal challenge that requires integrating visual features with specialized clinical knowledge. While vision-language pretraining…

cs.CV2024

CtrlNeRF: The Generative Neural Radiation Fields for the Controllable Synthesis of High-fidelity 3D-Aware Images

Jian Liu, Zhen Yu

The neural radiance field (NERF) advocates learning the continuous representation of 3D geometry through a multilayer perceptron (MLP). By integrating this into a generative model,…

cs.CV2022

Skin Lesion Recognition with Class-Hierarchy Regularized Hyperbolic Embeddings

Zhen Yu, Toan Nguyen, Yaniv Gal +7

In practice, many medical datasets have an underlying taxonomy defined over the disease label space. However, existing classification algorithms for medical diagnoses often assume…

stat.ME2020

Communication-Efficient Distributed Estimator for Generalized Linear Models with a Diverging Number of Covariates

Ping Zhou, Zhen Yu, Jingyi Ma +2

Distributed statistical inference has recently attracted immense attention. The asymptotic efficiency of the maximum likelihood estimator (MLE), the one-step MLE, and the aggregate…

cond-mat.mes-hall2004

Electrical properties of 0.4 cm long single-walled carbon nanotubes

Shengdong Li, Zhen Yu, Christopher Rutherglen +1

Centimeter scale aligned carbon nanotube arrays are grown from nanoparticle metal catalyst pads. We find the nanotubes grow both with and against the wind. A metal underlayer provi…

cs.CV2025

Controllable Skin Synthesis via Lesion-Focused Vector Autoregression Model

Jiajun Sun, Zhen Yu, Siyuan Yan +3

Skin images from real-world clinical practice are often limited, resulting in a shortage of training data for deep-learning models. While many studies have explored skin image synt…

cs.CV2025

Flexible Sampling for Long-tailed Skin Lesion Classification

Lie Ju, Yicheng Wu, Lin Wang +5

Most of the medical tasks naturally exhibit a long-tailed distribution due to the complex patient-level conditions and the existence of rare diseases. Existing long-tailed learning…

cs.CV2023

Hierarchical Knowledge Guided Learning for Real-world Retinal Diseases Recognition

Lie Ju, Zhen Yu, Lin Wang +4

In the real world, medical datasets often exhibit a long-tailed data distribution (i.e., a few classes occupy the majority of the data, while most classes have only a limited numbe…

cs.CE2026

RoadFed: A Multimodal Federated Learning System for Improving Road Safety

Yachao Yuan, Zhen Yu, Yali Yuan +3

Internet of Things (IoTs) have been widely applied in Collaborative Intelligent Transportation Systems (C-ITS) for the prevention of road accidents. As one of the primary causes of…

cs.LG2026

Interpretable Machine Learning for Antepartum Prediction of Pregnancy-Associated Thrombotic Microangiopathy Using Routine Longitudinal Laboratory Data

Chuanchuan Sun, Zhen Yu, Qin Fan +2

Background: Pregnancy-associated thrombotic microangiopathy (P-TMA) is rare but life-threatening. Early risk prediction before overt clinical presentation remains challenging, as t…

cs.DC2025

FedAPTA: Federated Multi-task Learning for Heterogeneous Devices with Adaptive Layer-wise Pruning and Task-aware Aggregation

Zhen Yu, Yachao Yuan, Jin Wang +2

Federated Learning (FL) has shown considerable promise in Machine Learning (ML) across numerous devices for privacy protection, efficient data utilization, and dynamic collaboratio…

cs.CV2025

RetinaGuard: Obfuscating Retinal Age in Fundus Images for Biometric Privacy Preserving

Zhengquan Luo, Chi Liu, Dongfu Xiao +3

The integration of AI with medical images enables the extraction of implicit image-derived biomarkers for a precise health assessment. Recently, retinal age, a biomarker predicted…