Yudong Zhang
YOU?
Author Swipe
View article: Impact of Riolan arch and mesenteric vascular anatomy on tissue oxygenation in rectal cancer surgery: A prospective study on inferior mesenteric artery ligation strategies
Impact of Riolan arch and mesenteric vascular anatomy on tissue oxygenation in rectal cancer surgery: A prospective study on inferior mesenteric artery ligation strategies Open
View article: VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models Open
Despite the remarkable success of Vision-Language Models (VLMs), their performance on a range of complex visual tasks is often hindered by a "visual processing bottleneck": a propensity to lose grounding in visual evidence and exhibit a de…
View article: Parameter Identification of Photovoltaic Models Using an Enhanced INFO Algorithm
Parameter Identification of Photovoltaic Models Using an Enhanced INFO Algorithm Open
Photovoltaic (PV) systems are electrical systems designed to convert solar energy into electrical energy. As a crucial component of PV systems, harsh weather conditions, photovoltaic panel temperature and solar irradiance influence the pow…
View article: AgentAsk: Multi-Agent Systems Need to Ask
AgentAsk: Multi-Agent Systems Need to Ask Open
Multi-agent systems built on large language models (LLMs) promise enhanced problem-solving capabilities through collaborative division of labor. However, they frequently underperform single-agent baselines due to edge-level error cascades:…
View article: Accurate and timely intraoperative classification of vocal cord leukoplakia by machine learning assisted handheld OCT
Accurate and timely intraoperative classification of vocal cord leukoplakia by machine learning assisted handheld OCT Open
Precise and timely intraoperative classification of vocal cord leukoplakia is vital for early staging and detection of laryngeal cancer. Current endoscopic imaging, such as narrow-band imaging (NBI) and white-light laryngoscopy (WLI), has …
View article: A lightweight hybrid model for scalable and robust plant leaf disease classification
A lightweight hybrid model for scalable and robust plant leaf disease classification Open
Plant leaf diseases significantly impact crop yield and quality, causing substantial economic loss and risking food security. Despite significant progress in the field of automated plant disease diagnosis, there are still several challenge…
View article: Prediction of the tensile strength of sandstones using image processing and GMDH techniques
Prediction of the tensile strength of sandstones using image processing and GMDH techniques Open
The tensile strength of rock plays a crucial role in the planning of tunnels and underground engineering projects. Given the inefficiency of the direct method in measuring this strength, non-destructive testing methods are now being employ…
View article: Hydrogen crossover raises serious concerns on proton exchange membrane water electrolyzer
Hydrogen crossover raises serious concerns on proton exchange membrane water electrolyzer Open
View article: Association between weight-adjusted waist circumference index and risk of cognitive decline in Chinese hypertensive patients: a case-control study
Association between weight-adjusted waist circumference index and risk of cognitive decline in Chinese hypertensive patients: a case-control study Open
Background As a new obesity-related index, the weight-adjusted waist circumference index (WWI) seems to be a good predictor of cognitive decline in hypertensive patients. This study aimed to verify the relationship between WWI and cognitiv…
View article: Study of municipal solid waste incinerator bottom ash (MSWIBA) and coal fly ash (CFA) applied to concrete pavement bricks: Mechanical properties, microstructure, durability
Study of municipal solid waste incinerator bottom ash (MSWIBA) and coal fly ash (CFA) applied to concrete pavement bricks: Mechanical properties, microstructure, durability Open
View article: The Security Threat of Compressed Projectors in Large Vision-Language Models
The Security Threat of Compressed Projectors in Large Vision-Language Models Open
The choice of a suitable visual language projector (VLP) is critical to the successful training of large visual language models (LVLMs). Mainstream VLPs can be broadly categorized into compressed and uncompressed projectors, and each offer…
View article: MSLAU-Net: A Hybird CNN-Transformer Network for Medical Image Segmentation
MSLAU-Net: A Hybird CNN-Transformer Network for Medical Image Segmentation Open
Both CNN-based and Transformer-based methods have achieved remarkable success in medical image segmentation tasks. However, CNN-based methods struggle to effectively capture global contextual information due to the inherent limitations of …
View article: FCFDiff-Net: full-conditional feature diffusion embedded network for 3D brain tumor segmentation
FCFDiff-Net: full-conditional feature diffusion embedded network for 3D brain tumor segmentation Open
The proposed FCFDiff-Net provides an efficient and robust solution for 3D BraTS, outperforming existing models in terms of accuracy and robustness. Future work will focus on exploring the model's generalization capabilities and conducting …
View article: Diff‐<scp>CFFBNet</scp>: Diffusion‐Embedded Cross‐Layer Feature Fusion Bridge Network for Brain Tumor Segmentation
Diff‐<span>CFFBNet</span>: Diffusion‐Embedded Cross‐Layer Feature Fusion Bridge Network for Brain Tumor Segmentation Open
This study introduces the Diff‐CFFBNet, a novel network for brain tumor segmentation designed to address the challenges of misdetection in broken tumor regions within MRI scans, which is crucial for early diagnosis, treatment planning, and…
View article: QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models
QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models Open
In typical multimodal tasks, such as Visual Question Answering (VQA), adversarial attacks targeting a specific image and question can lead large vision-language models (LVLMs) to provide incorrect answers. However, it is common for a singl…
View article: Revolutionizing antibiotic therapy: Polymyxin B and Fe2+-enriched liposomal carrier harness novel bacterial ferroptosis mechanism to combat resistant infections
Revolutionizing antibiotic therapy: Polymyxin B and Fe2+-enriched liposomal carrier harness novel bacterial ferroptosis mechanism to combat resistant infections Open
To address the pressing issue of bacterial resistance, antibiotics with new mechanisms were urgently needed; yet, the majority of efforts centered on discovering novel structural compounds, often plagued by lengthy research timelines and u…
View article: WaveNet-SF: A Hybrid Network for Retinal Disease Detection Based on Wavelet Transform in Spatial-Frequency Domain
WaveNet-SF: A Hybrid Network for Retinal Disease Detection Based on Wavelet Transform in Spatial-Frequency Domain Open
Retinal diseases are a leading cause of vision impairment and blindness, with timely diagnosis being critical for effective treatment. Optical Coherence Tomography (OCT) has become a standard imaging modality for retinal disease diagnosis,…
View article: Dislocation dissociation assisted formation mechanism of sigma phase and its impact on producing heterogeneous lamellar microstructure in CoCrV medium-entropy alloy
Dislocation dissociation assisted formation mechanism of sigma phase and its impact on producing heterogeneous lamellar microstructure in CoCrV medium-entropy alloy Open
View article: Forecasting Renewable Energy Consumption Using a Novel Fractional Grey Reverse Accumulation Model
Forecasting Renewable Energy Consumption Using a Novel Fractional Grey Reverse Accumulation Model Open
The accumulation operation is the most fundamental method for processing data in grey models, playing a decisive role in the accuracy of model predictions. However, the traditional forward accumulation method does not adhere to the princip…
View article: From Data to Deployment: A Comprehensive Analysis of Risks in Large Language Model Research and Development
From Data to Deployment: A Comprehensive Analysis of Risks in Large Language Model Research and Development Open
Large language models (LLMs) have evolved significantly, achieving unprecedented linguistic capabilities that underpin a wide range of AI applications. However, they also pose risks and challenges such as ethical concerns, bias and computa…
View article: QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models
QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models Open
View article: GM2FFNet: Grouped Multiscale Multiangle Feature Fusion Network With Center Attention for Hyperspectral Image Classification
GM2FFNet: Grouped Multiscale Multiangle Feature Fusion Network With Center Attention for Hyperspectral Image Classification Open
Convolutional neural networks and transformers have been extensively utilized in hyperspectral image classification due to their exceptional feature learning capabilities. However, many existing patch-based classification methods often neg…
View article: The Security Threat of Compressed Projectors in Large Vision-Language Models
The Security Threat of Compressed Projectors in Large Vision-Language Models Open
View article: Clip-Adafusion: Adaptive Multi-Modal Fusion for Composed Image Retrieval
Clip-Adafusion: Adaptive Multi-Modal Fusion for Composed Image Retrieval Open
View article: Triphenylmethane-Based Single-Component Ultralong Room Temperature Phosphorescence
Triphenylmethane-Based Single-Component Ultralong Room Temperature Phosphorescence Open
View article: Esc-Cafnet: A Multimodal Brain Tumor Segmentation Network Based on Enhanced Separable Convolution and Context-Aware Fusion
Esc-Cafnet: A Multimodal Brain Tumor Segmentation Network Based on Enhanced Separable Convolution and Context-Aware Fusion Open
View article: Triphenylmethane-Based Single-Component Ultralong Room Temperature Phosphorescence
Triphenylmethane-Based Single-Component Ultralong Room Temperature Phosphorescence Open
View article: FuzH-PID: Highly controllable and stable DNN for COVID-19 detection via improved stochastic optimization
FuzH-PID: Highly controllable and stable DNN for COVID-19 detection via improved stochastic optimization Open
View article: MADRL Based Joint Resource Allocation and 3D CoordinateOptimization of UAVs in Air-Ground Integrated IoT Networks
MADRL Based Joint Resource Allocation and 3D CoordinateOptimization of UAVs in Air-Ground Integrated IoT Networks Open
View article: LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer
LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer Open
Vision transformers (ViTs) are widely employed in multimodal large language models (MLLMs) for visual encoding. However, they exhibit inferior performance on tasks regarding fine-grained visual perception. We attribute this to the limitati…