arXiv subjects

Xianyan Chen

Publications and source records attributed to Xianyan Chen.

12 recordsLinked to original sources

arXiv2026

IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Review

Scientific research relies on accurate information retrieval from literature to support analytical decisions. In this work, we introduce a new task, INformation reTRieval through literAture reVIEW (IntraView), which aims to automate fine-grained information retrieval faithfully grounded in the provided content in response to research-driven queries, and propose IntrAgent, an LLM-based agent that addresses this challenging task. In particular, IntrAgent is designed to mimic human behaviors when reading literature for information retrieval -- identifying relevant sections and then iteratively extracting key details to refine the retrieved information. It follows a two-stage pipeline: a Section Ranking stage that prioritizes relevant literature sections through structural-knowledge-enabled reasoning, and an Iterative Reading stage that continuously extracts details and synthesizes them into concise, contextually grounded answers. To support rigorous evaluation, we introduce IntraBench, a new benchmark consisting of 315 test instances built from expert-authored questions paired with literature spanning five STEM domains. Across seven backbone LLMs, IntrAgent achieves on average 13.2% higher cross-domain accuracy than state-of-the-art RAG and research-agent baselines.

cs.IR↗

arXiv2026

Stiff-FCS: Single-Cell Stiffness Profiling With Integrated Molecular and Functional Analysis

Cell stiffness is a key determinant of how cells deform, migrate, and adapt to mechanically restrictive environments, yet existing single-cell stiffness assays remain difficult to combine with molecular analysis and downstream functional studies. To address these limitations, we introduce a microfluidic platform, stiffness-based ferrohydrodynamic cell sorting (Stiff-FCS), designed for high-throughput quantification of single-cell stiffness, on-chip molecular analysis, and post-assay cell recovery. Stiff-FCS combines ferrofluid-driven actuation with graded confinement channels to control cell movement, induce deformation, and spatially separate cells based on stiffness. An inverse computational model converts cell position and morphology into quantitative Young's modulus values. We demonstrate stiffness profiling of hundreds to thousands of cells per chip within minutes, same-cell fluorescence-based protein analysis, and recovery of stiffness-defined cells for downstream assays. Across diverse human and mouse cell lines, Lamin A/C showed the most consistent association with stiffness, whereas softer cells exhibited greater migratory capacity than stiffer cells. In a series of human head and neck cancer cell models, Stiff-FCS further resolved a stiff, less migratory subpopulation enriched in a higher-molecular-weight Vimentin state, offering a workflow for linking single-cell stiffness to molecular heterogeneity and cell behavior.

q-bio.CB↗

arXiv2026

Tau-induced atrophy drives functional connectivity disruption in Alzheimer's disease

Alzheimer's disease involves progressive tau accumulation and spread, leading to regional brain atrophy and disruption of large-scale functional networks. While tau propagation and tissue degeneration have been widely modeled, how atrophy dynamics translate into functional connectivity (FC) degradation remains unclear. Here, we develop a multiphysics framework integrating anisotropic tau reaction-diffusion, finite-deformation biomechanics, and network modeling to link tau-driven atrophy with FC changes. Model fidelity is evaluated by quantitatively comparing simulated atrophy patterns with imaging-derived measurements. Using longitudinal structural and functional MRI, we identify an approximately linear relationship between regional atrophy rates and FC change. We then construct an atrophy-informed structural network degradation matrix from model-predicted region-specific atrophy rates and embed it into a neural oscillation model to predict FC disruption. Our results show that (i) the coupled reaction-diffusion-biomechanical model reproduces observed regional atrophy, (ii) regional atrophy rates parsimoniously predict longitudinal FC changes, and (iii) the atrophy-informed degradation matrix captures the direction and relative magnitude of regional FC disruption. By converting tau-driven atrophy into predictive FC trajectories, the proposed framework offers a clinically interpretable avenue for forecasting disease progression and informing trial design.

physics.med-ph↗

arXiv2025

Ferrohydrodynamic Microfluidics for Bioparticle Separation and Single-Cell Phenotyping: Principles, Applications, and Emerging Directions

Ferrohydrodynamic microfluidics relies on magnetic field gradients to manipulate diamagnetic particles in ferrofluid-filled microenvironments. It has emerged as a promising tool for label-free manipulation of bioparticles, including their separation and phenotyping. This perspective reviews recent progress in the development and applications of ferrofluid-based microfluidic platforms for multiscale bioparticle separation, ranging from micron-scale cells to submicron extracellular vesicles. We highlight the fundamental physical principles for ferrohydrodynamic manipulation, including the dominant magnetic buoyancy force resulting from the interaction of ferrofluids and particles. We then describe how these principles enable high-resolution size-based bioparticle separation, subcellular bioparticle enrichment, and phenotypic screening based on physical traits. We also discuss key challenges in ferrohydrodynamic microfluidics from the aspects of ferrofluid biocompatibility, system throughput, and nanoparticle depletion. Finally, we outline future research directions involving machine learning, 3D printing, and multiplexed detection. These insights chart a path for advancing ferrofluid-based technologies in precision biomedicine, diagnostics, and cellular engineering.

eess.SY↗

arXiv2025

Automatic Classification of Circulating Blood Cell Clusters based on Multi-channel Flow Cytometry Imaging

Circulating blood cell clusters (CCCs) containing red blood cells (RBCs), white blood cells(WBCs), and platelets are significant biomarkers linked to conditions like thrombosis, infection, and inflammation. Flow cytometry, paired with fluorescence staining, is commonly used to analyze these cell clusters, revealing cell morphology and protein profiles. While computational approaches based on machine learning have advanced the automatic analysis of single-cell flow cytometry images, there is a lack of effort to build tools to automatically analyze images containing CCCs. Unlike single cells, cell clusters often exhibit irregular shapes and sizes. In addition, these cell clusters often consist of heterogeneous cell types, which require multi-channel staining to identify the specific cell types within the clusters. This study introduces a new computational framework for analyzing CCC images and identifying cell types within clusters. Our framework uses a two-step analysis strategy. First, it categorizes images into cell cluster and non-cluster groups by fine-tuning the You Only Look Once(YOLOv11) model, which outperforms traditional convolutional neural networks (CNNs), Vision Transformers (ViT). Then, it identifies cell types by overlaying cluster contours with regions from multi-channel fluorescence stains, enhancing accuracy despite cell debris and staining artifacts. This approach achieved over 95% accuracy in both cluster classification and phenotype identification. In summary, our automated framework effectively analyzes CCC images from flow cytometry, leveraging both bright-field and fluorescence data. Initially tested on blood cells, it holds potential for broader applications, such as analyzing immune and tumor cell clusters, supporting cellular research across various diseases.

cs.CV↗

arXiv2025

SoSBench: Benchmarking Safety Alignment on Six Scientific Domains

Large language models (LLMs) exhibit advancing capabilities in complex tasks, such as reasoning and graduate-level question answering, yet their resilience against misuse, particularly involving scientifically sophisticated risks, remains underexplored. Existing safety benchmarks typically focus either on instructions requiring minimal knowledge comprehension (e.g., ``tell me how to build a bomb") or utilize prompts that are relatively low-risk (e.g., multiple-choice or classification tasks about hazardous content). Consequently, they fail to adequately assess model safety when handling knowledge-intensive, hazardous scenarios. To address this critical gap, we introduce SoSBench, a regulation-grounded, hazard-focused benchmark encompassing six high-risk scientific domains: chemistry, biology, medicine, pharmacology, physics, and psychology. The benchmark comprises 3,000 prompts derived from real-world regulations and laws, systematically expanded via an LLM-assisted evolutionary pipeline that introduces diverse, realistic misuse scenarios (e.g., detailed explosive synthesis instructions involving advanced chemical formulas). We evaluate frontier models within a unified evaluation framework using our SoSBench. Despite their alignment claims, advanced models consistently disclose policy-violating content across all domains, demonstrating alarmingly high rates of harmful responses (e.g., 84.9% for Deepseek-R1 and 50.3% for GPT-4.1). These results highlight significant safety alignment deficiencies and underscore urgent concerns regarding the responsible deployment of powerful LLMs.

cs.LG↗

arXiv2025

A Multi-Agent Framework Integrating Large Language Models and Generative AI for Accelerated Metamaterial Design

Metamaterials, renowned for their exceptional mechanical, electromagnetic, and thermal properties, hold transformative potential across diverse applications, yet their design remains constrained by labor-intensive trial-and-error methods and limited data interoperability. Here, we introduce CrossMatAgent -- a novel multi-agent framework that synergistically integrates large language models with state-of-the-art generative AI to revolutionize metamaterial design. By orchestrating a hierarchical team of agents -- each specializing in tasks such as pattern analysis, architectural synthesis, prompt engineering, and supervisory feedback -- our system leverages the multimodal reasoning of GPT-4o alongside the generative precision of DALL-E 3 and a fine-tuned Stable Diffusion XL model. This integrated approach automates data augmentation, enhances design fidelity, and produces simulation- and 3D printing-ready metamaterial patterns. Comprehensive evaluations, including CLIP-based alignment, SHAP interpretability analyses, and mechanical simulations under varied load conditions, demonstrate the framework's ability to generate diverse, reproducible, and application-ready designs. CrossMatAgent thus establishes a scalable, AI-driven paradigm that bridges the gap between conceptual innovation and practical realization, paving the way for accelerated metamaterial development.

cond-mat.mtrl-sci↗

arXiv2024

PharmacyGPT: The AI Pharmacist

In this study, we introduce PharmacyGPT, a novel framework to assess the capabilities of large language models (LLMs) such as ChatGPT and GPT-4 in emulating the role of clinical pharmacists. Our methodology encompasses the utilization of LLMs to generate comprehensible patient clusters, formulate medication plans, and forecast patient outcomes. We conduct our investigation using real data acquired from the intensive care unit (ICU) at the University of North Carolina Chapel Hill (UNC) Hospital. Our analysis offers valuable insights into the potential applications and limitations of LLMs in the field of clinical pharmacy, with implications for both patient care and the development of future AI-driven healthcare solutions. By evaluating the performance of PharmacyGPT, we aim to contribute to the ongoing discourse surrounding the integration of artificial intelligence in healthcare settings, ultimately promoting the responsible and efficacious use of such technologies.

cs.CL↗

arXiv2024

Role of Data-driven Regional Growth Model in Shaping Brain Folding Patterns

The surface morphology of the developing mammalian brain is crucial for understanding brain function and dysfunction. Computational modeling offers valuable insights into the underlying mechanisms for early brain folding. Recent findings indicate significant regional variations in brain tissue growth, while the role of these variations in cortical development remains unclear. In this study, we unprecedently explored how regional cortical growth affects brain folding patterns using computational simulation. We first developed growth models for typical cortical regions using machine learning (ML)-assisted symbolic regression, based on longitudinal real surface expansion and cortical thickness data from prenatal and infant brains derived from over 1,000 MRI scans of 735 pediatric subjects with ages ranging from 29 post-menstrual weeks to 24 months. These models were subsequently integrated into computational software to simulate cortical development with anatomically realistic geometric models. We comprehensively quantified the resulting folding patterns using multiple metrics such as mean curvature, sulcal depth, and gyrification index. Our results demonstrate that regional growth models generate complex brain folding patterns that more closely match actual brains structures, both quantitatively and qualitatively, compared to conventional uniform growth models. Growth magnitude plays a dominant role in shaping folding patterns, while growth trajectory has a minor influence. Moreover, multi-region models better capture the intricacies of brain folding than single-region models. Our results underscore the necessity and importance of incorporating regional growth heterogeneity into brain folding simulations, which could enhance early diagnosis and treatment of cortical malformations and neurodevelopmental disorders such as cerebral palsy and autism.

q-bio.NC↗

arXiv2024

Automated Data-Driven Discovery of Material Models Based on Symbolic Regression: A Case Study on Human Brain Cortex

We introduce a data-driven framework to automatically identify interpretable and physically meaningful hyperelastic constitutive models from sparse data. Leveraging symbolic regression, an algorithm based on genetic programming, our approach generates elegant hyperelastic models that achieve accurate data fitting through parsimonious mathematic formulae, while strictly adhering to hyperelasticity constraints such as polyconvexity. Our investigation spans three distinct hyperelastic models -- invariant-based, principal stretch-based, and normal strain-based -- and highlights the versatility of symbolic regression. We validate our new approach using synthetic data from five classic hyperelastic models and experimental data from the human brain to demonstrate algorithmic efficacy. Our results suggest that our symbolic regression robustly discovers accurate models with succinct mathematic expressions in invariant-based, stretch-based, and strain-based scenarios. Strikingly, the strain-based model exhibits superior accuracy, while both stretch- and strain-based models effectively capture the nonlinearity and tension-compression asymmetry inherent to human brain tissue. Polyconvexity examinations affirm the rigor of convexity within the training regime and demonstrate excellent extrapolation capabilities beyond this regime for all three models. However, the stretch-based models raise concerns regarding potential convexity loss under large deformations. Finally, robustness tests on noise-embedded data underscore the reliability of our symbolic regression algorithms. Our study confirms the applicability and accuracy of symbolic regression in the automated discovery of hyperelastic models for the human brain and gives rise to a wide variety of applications in other soft matter systems.

cs.SC↗

arXiv2024

Assessing Large Language Models in Mechanical Engineering Education: A Study on Mechanics-Focused Conceptual Understanding

This study is a pioneering endeavor to investigate the capabilities of Large Language Models (LLMs) in addressing conceptual questions within the domain of mechanical engineering with a focus on mechanics. Our examination involves a manually crafted exam encompassing 126 multiple-choice questions, spanning various aspects of mechanics courses, including Fluid Mechanics, Mechanical Vibration, Engineering Statics and Dynamics, Mechanics of Materials, Theory of Elasticity, and Continuum Mechanics. Three LLMs, including ChatGPT (GPT-3.5), ChatGPT (GPT-4), and Claude (Claude-2.1), were subjected to evaluation against engineering faculties and students with or without mechanical engineering background. The findings reveal GPT-4's superior performance over the other two LLMs and human cohorts in answering questions across various mechanics topics, except for Continuum Mechanics. This signals the potential future improvements for GPT models in handling symbolic calculations and tensor analyses. The performances of LLMs were all significantly improved with explanations prompted prior to direct responses, underscoring the crucial role of prompt engineering. Interestingly, GPT-3.5 demonstrates improved performance with prompts covering a broader domain, while GPT-4 excels with prompts focusing on specific subjects. Finally, GPT-4 exhibits notable advancements in mitigating input bias, as evidenced by guessing preferences for humans. This study unveils the substantial potential of LLMs as highly knowledgeable assistants in both mechanical pedagogy and scientific research.

cs.CL↗

arXiv2023

Exploring hyperelastic material model discovery for human brain cortex: multivariate analysis vs. artificial neural network approaches

Traditional computational methods, such as the finite element analysis, have provided valuable insights into uncovering the underlying mechanisms of brain physical behaviors. However, precise predictions of brain physics require effective constitutive models to represent the intricate mechanical properties of brain tissue. In this study, we aimed to identify the most favorable constitutive material model for human brain tissue. To achieve this, we applied artificial neural network and multiple regression methods to a generalization of widely accepted classic models, and compared the results obtained from these two approaches. To evaluate the applicability and efficacy of the model, all setups were kept consistent across both methods, except for the approach to prevent potential overfitting. Our results demonstrate that artificial neural networks are capable of automatically identifying accurate constitutive models from given admissible estimators. Nonetheless, the five-term and two-term neural network models trained under single-mode and multi-mode loading scenarios, were found to be suboptimal and could be further simplified into two-term and single-term, respectively, with higher accuracy using multiple regression. Our findings highlight the importance of hyperparameters for the artificial neural network and emphasize the necessity for detailed cross-validations of regularization parameters to ensure optimal selection at a global level in the development of material constitutive models. This study validates the applicability and accuracy of artificial neural network to automatically discover constitutive material models with proper regularization as well as the benefits in model simplification without compromising accuracy for traditional multivariable regression.

cs.LG↗