arXiv subjects

Zhaoyi Zhang

Publications and source records attributed to Zhaoyi Zhang.

12 recordsLinked to original sources

arXiv2026

A Systematic Review of NLP for Ghanaian Languages: Datasets, Models, and a Research Roadmap

Natural Language Processing (NLP) for Ghana's 73 living indigenous languages remains deeply fragmented, under-resourced, and heavily skewed toward a single language. We present the first systematic review of the Ghanaian NLP landscape, screening 17,000+ publications across four academic databases to critically synthesize 36 core studies spanning datasets, model architectures, and evaluation paradigms. Our analysis exposes a severe resource imbalance: Twi-centric NLP has grown modestly, driven largely by religious-text alignment and crowdsourcing, while the remaining 70+ languages remain almost entirely unaddressed, and dataset releases, model checkpoints, and evaluation practices remain inconsistent and rarely shared across the field. We translate these findings into a prioritized roadmap targeting Ghana's acute regional constraints, dialectal variation, non-standardized orthographies, and the absence of shared infrastructure, offering a replicable template for systematic review and research prioritization in other low-resource language settings.

cs.CL↗

arXiv2026

Which LLM Is Your Ideal Companion? Evaluating Emotional Companion Capabilities of LLMs Based on Adult Attachment Theory

As large language models (LLMs) are increasingly applied for emotional companionship, evaluating their behavior and capabilities in intimate relationships has become a pressing issue. However, existing assessments primarily characterize general personality traits, providing limited insight into model behavior within intimate and emotionally sensitive contexts. Therefore, we introduce adult attachment theory into LLM evaluation and use the Experiences in Close Relationships-Revised (ECR-R) scale to characterize attachment anxiety and avoidance. To evaluate emotional companionship capabilities of LLMs in realistic interaction scenarios, we present an emotional companionship benchmark, ECBench, spanning four scenarios including emotional support, collaborative tasks, conflict resolution, and social guidance, across friendship and romantic relationships. ECBench is utilized to assess model behavior using 11 dialogue-quality metrics and three evaluation methods. We evaluate the attachment tendencies of 32 LLMs and select representative models to investigate how these tendencies manifest in contextualized multi-turn interactions and whether they can be shaped through prompting. Our study provides a theoretical lens from psychology, along with practical tools to understand and select LLMs for emotional companionship.

cs.CL↗

arXiv2026

MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models

Action-conditioned world models are increasingly used as scalable simulators for robot learning, yet current evaluations provide limited evidence that their predictions are reliable under the actions they condition on. Existing benchmarks largely emphasize visual fidelity, leaving unclear whether predicted futures are physically plausible, faithful to commanded actions, and calibrated to failure when actions should not succeed. We introduce \textsc{MiraBench}, a hierarchical benchmark that defines \emph{action-conditioned reliability} as a core evaluation target for robotic world models. MiraBench decomposes this target into three progressively demanding levels: \emph{Physics Adherence}, which evaluates reference-free physical consistency; \emph{Action-Following Fidelity}, which measures whether predictions respect task-relevant action inputs; and \emph{Optimism Bias Detection}, which probes the tendency to predict successful outcomes under failure-inducing actions. To support this evaluation, we curate a human-annotated corpus with over 16,000 judgments across tasks, failure categories, and leading world models. We evaluate 12 representative model configurations spanning vector-conditioned robotic world models, text-conditioned generative world models, open-weight systems, closed-source systems, and multiple model scales. Across this broad model landscape, MiraBench reveals three central findings: visual fidelity is a poor proxy for action fidelity; increasing model scale does not reliably improve action following; and optimism bias is pervasive across current systems. By shifting evaluation from appearance to action-conditioned reliability, MiraBench provides a diagnostic foundation for assessing and improving robotic world models as faithful simulators.

cs.AI↗

arXiv2025

Adversarial Distilled Retrieval-Augmented Guarding Model for Online Malicious Intent Detection

With the deployment of Large Language Models (LLMs) in interactive applications, online malicious intent detection has become increasingly critical. However, existing approaches fall short of handling diverse and complex user queries in real time. To address these challenges, we introduce ADRAG (Adversarial Distilled Retrieval-Augmented Guard), a two-stage framework for robust and efficient online malicious intent detection. In the training stage, a high-capacity teacher model is trained on adversarially perturbed, retrieval-augmented inputs to learn robust decision boundaries over diverse and complex user queries. In the inference stage, a distillation scheduler transfers the teacher's knowledge into a compact student model, with a continually updated knowledge base collected online. At deployment, the compact student model leverages top-K similar safety exemplars retrieved from the online-updated knowledge base to enable both online and real-time malicious query detection. Evaluations across ten safety benchmarks demonstrate that ADRAG, with a 149M-parameter model, achieves 98.5% of WildGuard-7B's performance, surpasses GPT-4 by 3.3% and Llama-Guard-3-8B by 9.5% on out-of-distribution detection, while simultaneously delivering up to 5.6x lower latency at 300 queries per second (QPS) in real-time applications.

cs.CR↗

arXiv2025

The African Languages Lab: A Collaborative Approach to Advancing Low-Resource African NLP

Despite representing nearly one-third of the world's languages, African languages remain critically underserved by modern NLP technologies, with 88\% classified as severely underrepresented or completely ignored in computational linguistics. We present the African Languages Lab (All Lab), a comprehensive research initiative that addresses this technological gap through systematic data collection, model development, and capacity building. Our contributions include: (1) a quality-controlled data collection pipeline, yielding the largest validated African multi-modal speech and text dataset spanning 40 languages with 19 billion tokens of monolingual text and 12,628 hours of aligned speech data; (2) extensive experimental validation demonstrating that our dataset, combined with fine-tuning, achieves substantial improvements over baseline models, averaging +23.69 ChrF++, +0.33 COMET, and +15.34 BLEU points across 31 evaluated languages; and (3) a structured research program that has successfully mentored fifteen early-career researchers, establishing sustainable local capacity. Our comparative evaluation against Google Translate reveals competitive performance in several languages while identifying areas that require continued development.

cs.CL↗

arXiv2025

Incremental dynamics of prestressed viscoelastic solids and its applications in shear wave elastography

Shear wave elastography (SWE) is a promising imaging modality for mechanical characterization of tissues, offering biomarkers with potential for early and precise diagnosis. While various methods have been developed to extract mechanical parameters from shear wave characteristics, their relationships in viscoelastic materials under prestress remain poorly understood. Here, we present a generalized incremental dynamics theory for finite-strain viscoelastic solids. The theory derives small-amplitude viscoelastic wave motions in a material under static pre-stress. The formalism is compatible with a range of existing constitutive models, including both hyperelasticity and viscoelasticity--such as the combination of Gasser-Ogden-Holzapfel (GOH) and Kelvin-Voigt fractional derivative (KVFD) models used in this study. We validate the theory through experiments and numerical simulations on prestressed soft materials and biological tissues, using both optical coherence elastography and ultrasound elastography. The theoretical predictions closely match experimental dispersion curves over a broad frequency range and accurately capture the effect of prestress. Furthermore, the framework reveals the relationships among shear wave phase velocity, attenuation, and principal stresses, enabling prestress quantification in viscoelastic solids without prior knowledge of constitutive parameters. This generalized acousto-viscoelastic formalism is particularly well-suited for high-frequency, high-resolution SWE in tissues under prestress.

cond-mat.soft↗

arXiv2025

Non-invasive measurement of local stress inside soft materials with programmed shear waves

Mechanical stresses in soft materials across different length scales play a fundamental role in understanding the function of biological systems and in the use of artificial materials for engineering soft machines and biomedical devices. Yet it remains a great challenge to probe local mechanical stresses in situ in a non-invasive, non-destructive manner, in particular when the mechanical properties are unknown. To address this challenge, we propose an acoustoelastic imaging-based method to infer the local mechanical stresses in soft materials by measuring the speed of shear waves induced by custom-programmed acoustic radiation force. Using a medical ultrasound transducer to excite and track the shear waves remotely, we demonstrate the application of the method by imaging uniaxial stress and bending stress in an isotropic hydrogel, and the passive uniaxial stress in a skeletal muscle. These measurements were all done without the knowledge of the constitutive parameters of the materials. These examples indicate that our method will find broad applications, ranging from health monitoring of soft structures and machines, to the diagnosis of diseases that alter stresses in soft tissues.

cond-mat.soft↗

arXiv2025

Research on a Two-Layer Demand Response Framework for Electric Vehicle Users and Aggregators Based on LLMs

The widespread adoption of electric vehicles (EVs) has increased the importance of demand response in smart grids. This paper proposes a two-layer demand response optimization framework for EV users and aggregators, leveraging large language models (LLMs) to balance electricity supply and demand and optimize energy utilization during EV charging. The upper-layer model, focusing on the aggregator, aims to maximize profits by adjusting retail electricity prices. The lower-layer model targets EV users, using LLMs to simulate charging demands under varying electricity prices and optimize both costs and user comfort. The study employs a multi-threaded LLM decision generator to dynamically analyze user behavior, charging preferences, and psychological factors. The framework utilizes the PSO method to optimize electricity prices, ensuring user needs are met while increasing aggregator profits. Simulation results show that the proposed model improves EV charging efficiency, alleviates peak power loads, and stabilizes smart grid operations.

eess.SY↗

arXiv2024

Simultaneous imaging of bidirectional guided waves enables synchronous probing of mechanical anisotropy, local blood pressure, and stress in arteries

Arterial biomechanical indicators have long been recognized as fundamental contributors to the physiology and pathology of cardiovascular systems. Probing the multiple biomechanical parameters of arteries simultaneously at different time points within one cardiac cycle is of great importance but remains challenging. Here we report an ultrasound elastography method to quantify arterial anisotropic stiffness, mechanical stresses in arterial wall, and local blood pressure in a single measurement. With programmed acoustic radiation force, arterial axial and circumferential guided elastic waves were induced simultaneously and recorded at multiple time points within one cardiac cycle. Then a mechanical model incorporating acoustoelasticity and viscoelasticity of arteries was proposed to quantitatively predict the correlation of arterial guided elastic waves with arterial biomechanical parameters. Our experimental design and biomechanical model lead to an elastography method to interrogate the variation of blood pressure, arterial bidirectional stiffnesses and mechanical stresses in arterial walls with time. In vivo experiments were performed on healthy young, normotensive older and hypertensive older volunteers. The results demonstrate that the reported method can find applications in understanding aging of cardiovascular system and diagnosis of cardiovascular diseases.

physics.med-ph↗

arXiv2022

SWENet: a physics-informed deep neural network (PINN) for shear wave elastography

Shear wave elastography (SWE) enables the measurement of elastic properties of soft materials, including soft tissues, in a non-invasive manner and finds broad applications in a variety of disciplines. The state-of-the-art SWE methods commercialized in various instruments rely on the measurement of shear wave velocities to infer material parameters and have relatively low resolution and accuracy for inhomogeneous soft materials due to the complexity of wave fields. In the present study, we overcome this challenge by proposing a physics-informed neural network (PINN)-based SWE (SWENet) method considering the merits of PINN in solving an inverse problem. The spatial variation of elastic properties of inhomogeneous materials has been defined in governing equations, which are encoded in PINN as loss functions. Snapshots of wave motion inside a local region have been used to train the neural networks, and during this course, the spatial distribution of elastic properties is inferred simultaneously. Both finite element simulations and tissue-mimicking phantom experiments have been performed to validate the method. Our results show that the shear moduli of soft composites consisting of matrix and inclusions of several millimeters in cross-section dimensions with either regular or irregular geometries can be identified with good accuracy. The advantages of the SWENet over conventional SWE methods consist of using more features of the wave motion in inhomogeneous soft materials and enabling seamless integration of multi-source data in the inverse analysis. Given the advantages of the reported method, it may find applications including but not limited to mechanical characterization of artificial soft biomaterials, imaging elastic properties of nerves in vivo, and differentiating small malignant tumors from benign ones by quantitatively measuring their distinct stiffnesses.

cond-mat.soft↗

arXiv2022

Towards a robust out-of-the-box neural network model for genomic data

The accurate prediction of biological features from genomic data is paramount for precision medicine and sustainable agriculture. For decades, neural network models have been widely popular in fields like computer vision, astrophysics and targeted marketing given their prediction accuracy and their robust performance under big data settings. Yet neural network models have not made a successful transition into the medical and biological world due to the ubiquitous characteristics of biological data such as modest sample sizes, sparsity, and extreme heterogeneity. Here, we investigate the robustness, generalization potential and prediction accuracy of widely used convolutional neural network and natural language processing models with a variety of heterogeneous genomic datasets. Mainly, recurrent neural network models outperform convolutional neural network models in terms of prediction accuracy, overfitting and transferability across the datasets under study. While the perspective of a robust out-of-the-box neural network model is out of reach, we identify certain model characteristics that translate well across datasets and could serve as a baseline model for translational researchers.

q-bio.GN↗

arXiv2020

Probing blood pressure and arterial stiffness noninvasively by guided axial waves

The clinical and economic burden of cardiovascular diseases (CVDs) poses a global challenge. Growing evidence suggests an early assessment of arterial stiffness can provide insights into the pathogenesis of CVDs. However, it remains difficult to quantitatively characterize the arterial stiffness in vivo. Here we utilize the guided elastic waves continuously excited and detected by ultrasound as a tool to probe the blood pressure (BP) and mechanical properties of the common carotid artery (CCA) simultaneously. In a pilot study of 17 healthy volunteers, we obverse a ~20% variation in the group velocity (5.16 m/s in systole and 4.31 m/s in diastole) induced by variation of the BP. A linear relationship between the square of the group velocity and the BP is revealed by our experimental data and finite element analysis, which enables us to measure the waveform of the BP. Furthermore, we propose to use the wavelet analysis to extract the dispersion relation of the guided waves, which provides a quantitative measurement of the arterial stiffness. The results and methods reported in this study show the group velocity and dispersion relation of the guided waves can be adopted to probe BP and arterial stiffness noninvasively and thus promising for early diagnosis of the CVDs.

physics.med-ph↗