arXiv subjects

Zhixuan Wang

Publications and source records attributed to Zhixuan Wang.

7 recordsLinked to original sources

arXiv2026

CArtBench: Evaluating Vision-Language Models on Chinese Art Understanding, Interpretation, and Authenticity

We introduce CARTBENCH, a museum-grounded benchmark for evaluating vision-language models (VLMs) on Chinese artworks beyond short-form recognition and QA. CARTBENCH comprises four subtasks: CURATORQA for evidence-grounded recognition and reasoning, CATALOGCAPTION for structured four-section expert-style appreciation, REINTERPRET for defensible reinterpretation with expert ratings, and CONNOISSEURPAIRS for diagnostic authenticity discrimination under visually similar confounds. CARTBENCH is built by aligning image-bearing Palace Museum objects from Wikidata with authoritative catalog pages, spanning five art categories across multiple dynasties. Across nine representative VLMs, we find that high overall CURATORQA accuracy can mask sharp drops on hard evidence linking and style-to-period inference; long-form appreciation remains far from expert references; and authenticity-oriented diagnostic discrimination stays near chance, underscoring the difficulty of connoisseur-level reasoning for current models.

cs.CL↗

arXiv2025

A Computational Approach to Epilepsy Treatment: An AI-optimized Global Natural Product Prescription System

Epilepsy is a prevalent neurological disease with millions of patients worldwide. Many patients have turned to alternative medicine due to the limited efficacy and side effects of conventional antiepileptic drugs. In this study, we developed a computational approach to optimize herbal epilepsy treatment through AI-driven analysis of global natural products and statistically validated randomized controlled trials (RCTs). Our intelligent prescription system combines machine learning (ML) algorithms for herb-efficacy characterization, Bayesian optimization for personalized dosing, and meta-analysis of RCTs for evidence-based recommendations. The system analyzed 1,872 natural compounds from traditional Chinese medicine (TCM), Ayurveda, and ethnopharmacological databases, integrating their bioactive properties with clinical outcomes from 48 RCTs covering 48 epilepsy conditions (n=5,216). Using LASSO regression and SHAP value analysis, we identified 17 high-efficacy herbs (e.g., Gastrodia elata [using é for accented characters], Withania somnifera), showing significant seizure reduction (p$<$0.01, Cohen's d=0.89) with statistical significance confirmed by multiple testing (p$<$0.001). A randomized double-blind validation trial (n=120) demonstrated 28.5\% greater seizure frequency reduction with AI-optimized herbal prescriptions compared to conventional protocols (95\% CI: 18.7-37.3\%, p=0.003).

q-bio.NC↗

arXiv2025

3D Deep-learning-based Segmentation of Human Skin Sweat Glands and Their 3D Morphological Response to Temperature Variations

Skin, the primary regulator of heat exchange, relies on sweat glands for thermoregulation. Alterations in sweat gland morphology play a crucial role in various pathological conditions and clinical diagnoses. Current methods for observing sweat gland morphology are limited by their two-dimensional, in vitro, and destructive nature, underscoring the urgent need for real-time, non-invasive, quantifiable technologies. We proposed a novel three-dimensional (3D) transformer-based multi-object segmentation framework, integrating a sliding window approach, joint spatial-channel attention mechanism, and architectural heterogeneity between shallow and deep layers. Our proposed network enables precise 3D sweat gland segmentation from skin volume data captured by optical coherence tomography (OCT). For the first time, subtle variations of sweat gland 3D morphology in response to temperature changes, have been visualized and quantified. Our approach establishes a benchmark for normal sweat gland morphology and provides a real-time, non-invasive tool for quantifying 3D structural parameters. This enables the study of individual variability and pathological changes in sweat gland structure, advancing dermatological research and clinical applications, including thermoregulation and bromhidrosis treatment.

eess.IV↗

arXiv2025

Intelligent Depression Prevention via LLM-Based Dialogue Analysis: Overcoming the Limitations of Scale-Dependent Diagnosis through Precise Emotional Pattern Recognition

Existing depression screening predominantly relies on standardized questionnaires (e.g., PHQ-9, BDI), which suffer from high misdiagnosis rates (18-34% in clinical studies) due to their static, symptom-counting nature and susceptibility to patient recall bias. This paper presents an AI-powered depression prevention system that leverages large language models (LLMs) to analyze real-time conversational cues--including subtle emotional expressions (e.g., micro-sentiment shifts, self-referential language patterns)--for more accurate and dynamic mental state assessment. Our system achieves three key innovations: (1) Continuous monitoring through natural dialogue, detecting depression-indicative linguistic features (anhedonia markers, hopelessness semantics) with 89% precision (vs. 72% for PHQ-9); (2) Adaptive risk stratification that updates severity levels based on conversational context, reducing false positives by 41% compared to scale-based thresholds; and (3) Personalized intervention strategies tailored to users' emotional granularity, demonstrating 2.3x higher adherence rates than generic advice. Clinical validation with 450 participants shows the system identifies 92% of at-risk cases missed by traditional scales, while its explainable AI interface bridges the gap between automated analysis and clinician judgment. This work establishes conversational AI as a paradigm shift from episodic scale-dependent diagnosis to continuous, emotionally intelligent mental health monitoring.

q-bio.NC↗

arXiv2024

A Novel Energy-Efficient Salicide-Enhanced Tunnel Device Technology Based on 300mm Foundry Platform Towards AIoT Applications

This work demonstrates a novel energy-efficient tunnel FET (TFET)-CMOS hybrid foundry platform for ultralow-power AIoT applications. By utilizing the proposed monolithic integration process, the novel complementary n and p-type Si TFET technology with dopant segregated source junction and self-aligned drain underlap design is successfully integrated into a 300mm CMOS baseline process without CMOS performance penalty and any new materials, experimentally demonstrating the large Ion and record high Ion/Ioff ratio of 10^7 among TFETs by industry-manufacturers. The device performance and variability are also co-optimized for high-volume production. Further circuit-level implementations are presented based on the calibrated compact model. The proposed TFET-CMOS hybrid logic and SRAM topologies show significant energy efficiency improvement with comparable operation speed compared with standard CMOS circuits, indicating its great potential for power-constraint AIoT applications.

cond-mat.mes-hall↗

arXiv2024

Advancing Multimodal Data Fusion in Pain Recognition: A Strategy Leveraging Statistical Correlation and Human-Centered Perspectives

This research presents a novel multimodal data fusion methodology for pain behavior recognition, integrating statistical correlation analysis with human-centered insights. Our approach introduces two key innovations: 1) integrating data-driven statistical relevance weights into the fusion strategy to effectively utilize complementary information from heterogeneous modalities, and 2) incorporating human-centric movement characteristics into multimodal representation learning for detailed modeling of pain behaviors. Validated across various deep learning architectures, our method demonstrates superior performance and broad applicability. We propose a customizable framework that aligns each modality with a suitable classifier based on statistical significance, advancing personalized and effective multimodal fusion. Furthermore, our methodology provides explainable analysis of multimodal data, contributing to interpretable and explainable AI in healthcare. By highlighting the importance of data diversity and modality-specific representations, we enhance traditional fusion techniques and set new standards for recognizing complex pain behaviors. Our findings have significant implications for promoting patient-centered healthcare interventions and supporting explainable clinical decision-making.

cs.AI↗

arXiv2021

Transport-Induced-Charge Electroosmosis

We report theoretical analysis of transport-induced-charge electroosmosis (TICEO) in a nanopore due to the presence of a local electric field and a conductivity gradient. TICEO shares a similar characteristic with classical induced-charge electroosmosis (ICEO) that the mean velocity $\overline{v_\text{TIC}}$ is proportional to the square of the applied electric potential difference $Δψ$, $i.e.$, $\overline{v_\text{TIC}} \propto (Δψ)^2$, appropriate for alternating current (AC) pumping applications. In contrast to ICEO which is primarily used in microfluidics, TICEO does not require metallic or dielectric patches and is thus suitable for nanopore pumping, providing new opportunities for AC nanopore applications.

physics.flu-dyn↗