Jun Xiao

CoFE: Collaborative Feature Engineering via Semantically-Guided Exploration and Diagnostic-Driven Refinement

Weihao Jiang, Zi-ang Nan, Zhihui Shi, Ya Cong et autres

In domains such as finance, healthcare, and industry, feature engineering remains the key bottleneck limiting the performance of machine learning models on tabular data. While Automated Feature Engineering (AutoFE) aims to reduce this manual effort, existing approaches still suffer from distinct limitations: …

cn (code pays fourni par la source)

Beyond Language Processing: LLMs Rules-Injected Instruction Tuning for Traffic Prediction

Weihao Jiang, Huizhao Wang, Zhihui Hu, Wenyu Hu et autres

Large Language Models (LLMs) demonstrate strong capabilities in contextual integration and multi-step reasoning, which endow them with the potential to model heterogeneous traffic data. However, the knowledge acquired during LLM pre-training is primarily qualitative and broad, and does not provide the fine-grained, …

cn (code pays fourni par la source)

A multimodal vision-language model for comprehensive dental diagnosis and enhanced clinical practice

Zijie Meng, Jin Hao, Xiwei Dai, Yang Feng et autres

Oral diseases affect billions of people, yet specialist dental expertise remains unevenly distributed, and diagnosis often requires synthesis across diverse imaging modalities. Existing artificial intelligence systems mostly address isolated tasks, limiting their applicability in comprehensive dental assessment. Here we introduce DentVLM, a …

cn, ca, sg, us (code pays fourni par la source)

A B cell-IgA-epithelial axis enhances antitumor immunity and improves outcome in HPV-associated penile squamous cell carcinoma

Tao Tao, Lianbang Zhu, Deyun Shen, Jiayang Zhang et autres

Penile squamous cell carcinoma (PSCC) is a rare, aggressive malignancy, with HPV driving approximately 50% of cases and correlating with improved outcomes. In this study, we perform single-cell RNA sequencing on tumor microenvironment (TME) cells from 23 treatment-naive PSCC patients, including 11 …

cn (code pays fourni par la source)

c-Myc-PANK3-EMT axis regulates the structure and function of intestinal barrier in ulcerative colitis

Shize Zhang, Yuang Chen, Nan Aa, Xu Chen et autres

INTRODUCTION: The repair of structural damage of the intestinal barrier is critical to rescue ulcerative colitis (UC), but there lacks effective targets currently. OBJECTIVES: This study aims to explore mechanisms and identify potential targets for repairing the damaged intestinal barrier involved in …

cn (code pays fourni par la source)

Rapid Onset of Cecal Ulcer After a Negative Colonoscopy: Primary Diffuse Large B-Cell Lymphoma of the Cecum

X Li, Tao Dong, Yaohui Wang, Jun Xiao

cn (code pays fourni par la source)

Compositional Zero-shot Learning via Progressive Language-based Observations

Lin Li, Guikun Chen, Zhen Wang, Jun Xiao et autres

Compositional zero-shot learning aims to recognize unseen stateobject compositions by leveraging known primitives (state and object) during training. However, effectively modeling interactions between primitives and generalizing knowledge to novel compositions remains a perennial challenge. There are two crucial factors: large object-conditioned and …

hk, cn (code pays fourni par la source)

Robust Modality-Incomplete Anomaly Detection: A Modality-Instructive Framework with Benchmark

Bingchen Miao, Wenqiao Zhang, Juncheng Li, Wangyu Wu et autres

Multimodal Industrial Anomaly Detection (MIAD)-fusing 3D point clouds and 2D RGB for product defect detection-is critical to quality inspection. However, existing MIAD methods assume all modalities are available and paired, overlooking real-scenario modality-missing and risking overfitting to incomplete data. To address these, …

cn, gb, ca (code pays fourni par la source)

Zero-shot Compositional Action Recognition with Neural Logic Constraints

G Ye, Lin Li, Kexin Li, Jun Xiao et autres

Zero-shot compositional action recognition (ZS-CAR) aims to identify unseen verb-object compositions in the videos by exploiting the learned knowledge of verb and object primitives during training. Despite compositional learning's progress in ZS-CAR, two critical challenges persist: 1) Missing compositional structure constraint, leading …

cn, hk (code pays fourni par la source)

EyecareGPT: Boosting Comprehensive Ophthalmology Understanding with Tailored Dataset, Benchmark and Model

Sijing Li, Lingshuai Lin, Wenqiao Zhang, Jiang Liu et autres

cn, sg (code pays fourni par la source)

Distal-less homeobox 5 transactivated by MYCN contributes to progression of neuroblastoma through AKT signaling pathway

Yi He, Xiaosi Yu, Chenzhao Feng, Ke Chen et autres

Neuroblastoma is one of the highest incidence solid tumors of childhood. Therapy for neuroblastoma with MYCN proto-oncogene (MYCN) amplification is of great challenge, due to its aggressive invasion and chemoresistance. In our study, differentially expressed genes (DEGs) between MYCN-amplified and non-amplified neuroblastoma …

cn (code pays fourni par la source)

GTCExplainer: Interpretable Graph Convolutional Networks for Molecular Activity Prediction

Jun Xiao, Dongjiang Niu, Qunhao Zhang, Zhixin Zhang et autres

ABSTRACT With the growing application of Graph Convolutional Networks (GCNs) across various domains, particularly in the field of bioinformatics, the demand for their interpretability has become more urgent. In bioinformatics, many critical tasks, including drug discovery and protein–ligand interaction analysis, rely heavily …

cn (code pays fourni par la source)