arXiv subjects

Wenyu Zhang

Publications and source records attributed to Wenyu Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Integrating Spatiotemporal Vision Transformer into Digital Twins for High-Resolution Heat Stress Forecasting in Campus Environments

Extreme heat events, exacerbated by climate change, pose significant challenges to urban resilience and planning. This study introduces a climate-responsive digital twin framework integrating the Spatiotemporal Vision Transformer (ST-ViT) model to enhance heat stress forecasting and decision-making. Using a Texas campus as a testbed, we synthesized high-resolution physical model simulations with spatial and meteorological data to develop fine-scale human thermal predictions. The ST-ViT-powered digital twin enables efficient, data-driven insights for planners and stakeholders, supporting targeted heat mitigation strategies and advancing climate-adaptive urban design. This campus-scale demonstration offers a foundation for future applications across broader and more diverse urban contexts.

cs.CV↗

arXiv2025

Qianfan-VL: Domain-Enhanced Universal Vision-Language Models

We present Qianfan-VL, a series of multimodal large language models ranging from 3B to 70B parameters, achieving state-of-the-art performance through innovative domain enhancement techniques. Our approach employs multi-stage progressive training and high-precision data synthesis pipelines, which prove to be critical technologies for enhancing domain-specific capabilities while maintaining strong general performance. Qianfan-VL achieves comparable results to leading open-source models on general benchmarks, with state-of-the-art performance on benchmarks such as CCBench, SEEDBench IMG, ScienceQA, and MMStar. The domain enhancement strategy delivers significant advantages in OCR and document understanding, validated on both public benchmarks (OCRBench 873, DocVQA 94.75%) and in-house evaluations. Notably, Qianfan-VL-8B and 70B variants incorporate long chain-of-thought capabilities, demonstrating superior performance on mathematical reasoning (MathVista 78.6%) and logical inference tasks. All models are trained entirely on Baidu's Kunlun P800 chips, validating the capability of large-scale AI infrastructure to train SOTA-level multimodal models with over 90% scaling efficiency on 5000 chips for a single task. This work establishes an effective methodology for developing domain-enhanced multimodal models suitable for diverse enterprise deployment scenarios.

cs.CV↗

arXiv2025

Cascading nuclear excitation of $^{235}\text{U}$ via inelastic electron scattering in laser-irradiated clusters

Nuclear excitation induced by lasers holds broad application prospects in precision metrology and nuclear energy, such as nuclear batteries and nuclear clocks. In the present work, the nuclear excitation via inelastic electron scattering (NEIES) mechanism in $^{235}\text{U}$ is investigated by combining the Dirac-Hartree-Fock-Slater method for theoretical calculations with 2D3V particle-in-cell (PIC) simulations for numerical modeling. The excitation cross-sections of $^{235}\text{U}$ from the ground state to excited states is evaluated and an efficient indirect excitation scheme for generating $^{235}\text{U}$ isomers is proposed by first exciting the nuclei from ground-state to high-energy excited states and then decays to the isomeric state. The calculations show that laser-tuned multi-channel NEIES can boost isomeric state accumulation efficiency by eleven orders of magnitude over direct excitation. Additionally, PIC simulations reveal that laser polarization significantly alters high-energy electron distributions. At identical intensity, p-polarized lasers generate seven times more electrons with energies sufficient for exciting $^{235}\text{U}$ to the second excited state (and beyond to the fourth state) compared to s-polarization. This work offers a practical and feasible way for efficient isomeric state generation, supporting experimental tests of laser-driven nuclear excitation in sub-TW lasers.

nucl-th↗

arXiv2025

Incorporating Contextual Paralinguistic Understanding in Large Speech-Language Models

Current large speech language models (Speech-LLMs) often exhibit limitations in empathetic reasoning, primarily due to the absence of training datasets that integrate both contextual content and paralinguistic cues. In this work, we propose two approaches to incorporate contextual paralinguistic information into model training: (1) an explicit method that provides paralinguistic metadata (e.g., emotion annotations) directly to the LLM, and (2) an implicit method that automatically generates novel training question-answer (QA) pairs using both categorical and dimensional emotion annotations alongside speech transcriptions. Our implicit method boosts performance (LLM-judged) by 38.41% on a human-annotated QA benchmark, reaching 46.02% when combined with the explicit approach, showing effectiveness in contextual paralinguistic understanding. We also validate the LLM judge by demonstrating its correlation with classification metrics, providing support for its reliability.

cs.CL↗

arXiv2025

SPHERE: Unveiling Spatial Blind Spots in Vision-Language Models Through Hierarchical Evaluation

Current vision-language models may grasp basic spatial cues and simple directions (e.g. left, right, front, back), but struggle with the multi-dimensional spatial reasoning necessary for human-like understanding and real-world applications. To address this gap, we develop SPHERE (Spatial Perception and Hierarchical Evaluation of REasoning), a hierarchical evaluation framework supported by a new human-annotated dataset. SPHERE systematically probes models across increasing levels of complexity, from fundamental skills to multi-skill integration and high-level reasoning that combines spatial, visual, and logical understanding. Benchmark evaluation of state-of-the-art models reveals significant deficiencies, especially in reasoning about distance and proximity, understanding both egocentric and allocentric perspectives, and applying spatial logic in physical contexts. These findings expose critical blind spots in existing models and underscore the need for more advanced spatial reasoning techniques, driving the development of vision-language models that align more closely with human spatial cognition. The SPHERE benchmark is available at https://github.com/zwenyu/SPHERE-VLM.

cs.CV↗

arXiv2025

Covariant analysis of electromagnetic current on the light cone: exposition with scalar Yukawa theory

We present the first systematic investigation of the Lorentz covariance of the charge form factor for a strongly coupled scalar theory in (3+1)-dimensions. Our results are based on the first non-perturbative solution of the scalar Yukawa theory with a Fock sector expansion including up to thee-particles (one mock nucleon plus two mock pions or two mock nucleons plus one mock anti-nucleon). The light-front Hamiltonian is constructed and renormalized using a Fock sector dependent scheme. The derived eigenvalue equation is then solved non-perturbatively to obtain the wave functions, which are then used to compute the current matrix element. We perform a covariant analysis of the current matrix element taking into account possible violation of the Poincaré symmetry due to the Fock sector truncation. The physical form factor depends on two boost invariants $ζ, Δ^2_\perp$, instead of the single Lorentz invariant $Q^2$. Instead of adopting the conventional Drell-Yan frame $ζ= 0$, we evaluate the form factor in general frames, and use the frame dependence to quantitatively gauge the loss of the Lorentz covariance. Our numerical result shows that as more Fock sectors are included, the frame dependence reduces dramatically. In particular, the anti-nucleon degree of freedom plays an important role in the reduction of the frame dependence, even though it only takes a small portion within the state vector. We also find that there is no zero-mode contribution to the current for the scalar Yukawa theory.

hep-ph↗

arXiv2025

AudioBench: A Universal Benchmark for Audio Large Language Models

We introduce AudioBench, a universal benchmark designed to evaluate Audio Large Language Models (AudioLLMs). It encompasses 8 distinct tasks and 26 datasets, among which, 7 are newly proposed datasets. The evaluation targets three main aspects: speech understanding, audio scene understanding, and voice understanding (paralinguistic). Despite recent advancements, there lacks a comprehensive benchmark for AudioLLMs on instruction following capabilities conditioned on audio signals. AudioBench addresses this gap by setting up datasets as well as desired evaluation metrics. Besides, we also evaluated the capabilities of five popular models and found that no single model excels consistently across all tasks. We outline the research outlook for AudioLLMs and anticipate that our open-sourced evaluation toolkit, data, and leaderboard will offer a robust testbed for future model developments.

cs.SD↗

arXiv2025

Detection of Sleep Apnea-Hypopnea Events Using Millimeter-wave Radar and Pulse Oximeter

Obstructive Sleep Apnea-Hypopnea Syndrome (OSAHS) is a sleep-related breathing disorder associated with significant morbidity and mortality worldwide. The gold standard for OSAHS diagnosis, polysomnography (PSG), faces challenges in popularization due to its high cost and complexity. Recently, radar has shown potential in detecting sleep apnea-hypopnea events (SAE) with the advantages of low cost and non-contact monitoring. However, existing studies, especially those using deep learning, employ segment-based classification approach for SAE detection, making the task of event quantity estimation difficult. Additionally, radar-based SAE detection is susceptible to interference from body movements and the environment. Oxygen saturation (SpO2) can offer valuable information about OSAHS, but it also has certain limitations and cannot be used alone for diagnosis. In this study, we propose a method using millimeterwave radar and pulse oximeter to detect SAE, called ROSA. It fuses information from both sensors, and directly predicts the temporal localization of SAE. Experimental results demonstrate a high degree of consistency (ICC=0.9864) between AHI from ROSA and PSG. This study presents an effective method with lowload device for the diagnosis of OSAHS.

eess.SP↗

arXiv2025

MoWE-Audio: Multitask AudioLLMs with Mixture of Weak Encoders

The rapid advancements in large language models (LLMs) have significantly enhanced natural language processing capabilities, facilitating the development of AudioLLMs that process and understand speech and audio inputs alongside text. Existing AudioLLMs typically combine a pre-trained audio encoder with a pre-trained LLM, which are subsequently finetuned on specific audio tasks. However, the pre-trained audio encoder has constrained capacity to capture features for new tasks and datasets. To address this, we propose to incorporate mixtures of `weak' encoders (MoWE) into the AudioLLM framework. MoWE supplements a base encoder with a pool of relatively light weight encoders, selectively activated based on the audio input to enhance feature extraction without significantly increasing model size. Our empirical results demonstrate that MoWE effectively improves multi-task performance, broadening the applicability of AudioLLMs to more diverse audio tasks.

cs.SD↗

arXiv2025

A Survey and Evaluation of Adversarial Attacks for Object Detection

Deep learning models achieve remarkable accuracy in computer vision tasks, yet remain vulnerable to adversarial examples--carefully crafted perturbations to input images that can deceive these models into making confident but incorrect predictions. This vulnerability pose significant risks in high-stakes applications such as autonomous vehicles, security surveillance, and safety-critical inspection systems. While the existing literature extensively covers adversarial attacks in image classification, comprehensive analyses of such attacks on object detection systems remain limited. This paper presents a novel taxonomic framework for categorizing adversarial attacks specific to object detection architectures, synthesizes existing robustness metrics, and provides a comprehensive empirical evaluation of state-of-the-art attack methodologies on popular object detection models, including both traditional detectors and modern detectors with vision-language pretraining. Through rigorous analysis of open-source attack implementations and their effectiveness across diverse detection architectures, we derive key insights into attack characteristics. Furthermore, we delineate critical research gaps and emerging challenges to guide future investigations in securing object detection systems against adversarial threats. Our findings establish a foundation for developing more robust detection models while highlighting the urgent need for standardized evaluation protocols in this rapidly evolving domain.

cs.CV↗

arXiv2025

Mapping Urban Villages in China: Progress and Challenges

The shift toward high-quality urbanization has brought increased attention to the issue of "urban villages", which has become a prominent social problem in China. However, there is a lack of available geospatial data on urban villages, making it crucial to prioritize urban village mapping. In order to assess the current progress in urban village mapping and identify challenges and future directions, we have conducted a comprehensive review, which to the best of our knowledge is the first of its kind in this field. Our review begins by providing a clear context for urban villages and elaborating the method for literature review, then summarizes the study areas, data sources, and approaches used for urban village mapping in China. We also address the challenges and future directions for further research. Through thorough investigation, we find that current studies only cover very limited study areas and periods and lack sufficient investigation into the scalability, transferability, and interpretability of identification approaches due to the challenges in concept fuzziness and variances, spatial heterogeneity and variances of urban villages, and data availability. Future research can complement and further the current research in the following potential directions in order to achieve large-area mapping across the whole nation...

cs.DB↗

arXiv2025

SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages

Southeast Asia (SEA) is a region rich in linguistic diversity and cultural variety, with over 1,300 indigenous languages and a population of 671 million people. However, prevailing AI models suffer from a significant lack of representation of texts, images, and audio datasets from SEA, compromising the quality of AI models for SEA languages. Evaluating models for SEA languages is challenging due to the scarcity of high-quality datasets, compounded by the dominance of English training data, raising concerns about potential cultural misrepresentation. To address these challenges, we introduce SEACrowd, a collaborative initiative that consolidates a comprehensive resource hub that fills the resource gap by providing standardized corpora in nearly 1,000 SEA languages across three modalities. Through our SEACrowd benchmarks, we assess the quality of AI models on 36 indigenous languages across 13 tasks, offering valuable insights into the current AI landscape in SEA. Furthermore, we propose strategies to facilitate greater AI advancements, maximizing potential utility and resource equity for the future of AI in SEA.

cs.CL↗

arXiv2025

Bridging Domain Gaps between Pretrained Multimodal Models and Recommendations

With the explosive growth of multimodal content online, pre-trained visual-language models have shown great potential for multimodal recommendation. However, while these models achieve decent performance when applied in a frozen manner, surprisingly, due to significant domain gaps (e.g., feature distribution discrepancy and task objective misalignment) between pre-training and personalized recommendation, adopting a joint training approach instead leads to performance worse than baseline. Existing approaches either rely on simple feature extraction or require computationally expensive full model fine-tuning, struggling to balance effectiveness and efficiency. To tackle these challenges, we propose \textbf{P}arameter-efficient \textbf{T}uning for \textbf{M}ultimodal \textbf{Rec}ommendation (\textbf{PTMRec}), a novel framework that bridges the domain gap between pre-trained models and recommendation systems through a knowledge-guided dual-stage parameter-efficient training strategy. This framework not only eliminates the need for costly additional pre-training but also flexibly accommodates various parameter-efficient tuning methods.

cs.IR↗

arXiv2025

Fusion of Millimeter-wave Radar and Pulse Oximeter Data for Low-burden Diagnosis of Obstructive Sleep Apnea-Hypopnea Syndrome

Objective: The aim of the study is to develop a novel method for improved diagnosis of obstructive sleep apnea-hypopnea syndrome (OSAHS) in clinical or home settings, with the focus on achieving diagnostic performance comparable to the gold-standard polysomnography (PSG) with significantly reduced monitoring burden. Methods: We propose a method using millimeter-wave radar and pulse oximeter for OSAHS diagnosis (ROSA). It contains a sleep apnea-hypopnea events (SAE) detection network, which directly predicts the temporal localization of SAE, and a sleep staging network, which predicts the sleep stages throughout the night, based on radar signals. It also fuses oxygen saturation (SpO2) information from the pulse oximeter to adjust the score of SAE detected by radar. Results: Experimental results on a real-world dataset (>800 hours of overnight recordings, 100 subjects) demonstrated high agreement (ICC=0.9870) on apnea-hypopnea index (AHI) between ROSA and PSG. ROSA also exhibited excellent diagnostic performance, exceeding 90% in accuracy across AHI diagnostic thresholds of 5, 15 and 30 events/h. Conclusion: ROSA improves diagnostic accuracy by fusing millimeter-wave radar and pulse oximeter data. It provides a reliable and low-burden solution for OSAHS diagnosis. Significance: ROSA addresses the limitations of high complexity and monitoring burden associated with traditional PSG. The high accuracy and low burden of ROSA show its potential to improve the accessibility of OSAHS diagnosis among population.

eess.SP↗

arXiv2025

MERaLiON-AudioLLM: Bridging Audio and Language with Large Language Models

We introduce MERaLiON-AudioLLM (Multimodal Empathetic Reasoning and Learning in One Network), the first speech-text model tailored for Singapore's multilingual and multicultural landscape. Developed under the National Large Language Models Funding Initiative, Singapore, MERaLiON-AudioLLM integrates advanced speech and text processing to address the diverse linguistic nuances of local accents and dialects, enhancing accessibility and usability in complex, multilingual environments. Our results demonstrate improvements in both speech recognition and task-specific understanding, positioning MERaLiON-AudioLLM as a pioneering solution for region specific AI applications. We envision this release to set a precedent for future models designed to address localised linguistic and cultural contexts in a global framework.

cs.CL↗

arXiv2025

Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal Models

Singlish, a Creole language rooted in English, is a key focus in linguistic research within multilingual and multicultural contexts. However, its spoken form remains underexplored, limiting insights into its linguistic structure and applications. To address this gap, we standardize and annotate the largest spoken Singlish corpus, introducing the Multitask National Speech Corpus (MNSC). These datasets support diverse tasks, including Automatic Speech Recognition (ASR), Spoken Question Answering (SQA), Spoken Dialogue Summarization (SDS), and Paralinguistic Question Answering (PQA). We release standardized splits and a human-verified test set to facilitate further research. Additionally, we propose SingAudioLLM, a multi-task multimodal model leveraging multimodal large language models to handle these tasks concurrently. Experiments reveal our models adaptability to Singlish context, achieving state-of-the-art performance and outperforming prior models by 10-30% in comparison with other AudioLLMs and cascaded solutions.

cs.CL↗

arXiv2024

SS-CTML: Self-Supervised Cross-Task Mutual Learning for CT Image Reconstruction

Supervised deep-learning (SDL) techniques with paired training datasets have been widely studied for X-ray computed tomography (CT) image reconstruction. However, due to the difficulties of obtaining paired training datasets in clinical routine, the SDL methods are still away from common uses in clinical practices. In recent years, self-supervised deep-learning (SSDL) techniques have shown great potential for the studies of CT image reconstruction. In this work, we propose a self-supervised cross-task mutual learning (SS-CTML) framework for CT image reconstruction. Specifically, a sparse-view scanned and a limited-view scanned sinogram data are first extracted from a full-view scanned sinogram data, which results in three individual reconstruction tasks, i.e., the full-view CT (FVCT) reconstruction, the sparse-view CT (SVCT) reconstruction, and limited-view CT (LVCT) reconstruction. Then, three neural networks are constructed for the three reconstruction tasks. Considering that the ultimate goals of the three tasks are all to reconstruct high-quality CT images, we therefore construct a set of cross-task mutual learning objectives for the three tasks, in which way, the three neural networks can be self-supervised optimized by learning from each other. Clinical datasets are adopted to evaluate the effectiveness of the proposed framework. Experimental results demonstrate that the SS-CTML framework can obtain promising CT image reconstruction performance in terms of both quantitative and qualitative measurements.

eess.IV↗

arXiv2024

Importance Sampling With Stochastic Particle Flow and Diffusion Optimization

Particle flow (PFL) is an effective method for overcoming particle degeneracy, the main limitation of particle filtering. In PFL, particles are migrated towards regions of high likelihood based on the solution of a partial differential equation. Recently proposed stochastic PFL introduces a diffusion term in the ordinary differential equation (ODE) that describes particle motion. This diffusion term reduces the stiffness of the ODE and makes it possible to perform PFL with a lower number of numerical integration steps compared to traditional deterministic PFL. In this work, we introduce a general approach to perform importance sampling (IS) based on stochastic PFL. Our method makes it possible to evaluate a "flow-induced" proposal probability density function (PDF) after the parameters of a Gaussian mixture model (GMM) have been migrated by stochastic PFL. Compared to conventional stochastic PFL, the resulting processing step is asymptotically optimal. Within our method, it is possible to optimize the diffusion matrix that describes the diffusion term of the ODE to improve the accuracy-computational complexity tradeoff. Our simulation results in a highly nonlinear 3-D source localization scenario showcase a reduced stiffness of the ODE and an improved estimating accuracy compared to state-of-the-art deterministic and stochastic PFL.

eess.SP↗