Ran Tao
YOU?
Author Swipe
View article: What Makes Diffusion Language Models Super Data Learners?
What Makes Diffusion Language Models Super Data Learners? Open
Recent studies have shown that diffusion language models achieve remarkable data efficiency under limited-data constraints, yet the underlying mechanisms remain unclear. In this work, we perform extensive ablation experiments to disentangl…
View article: Research on Speed Control of Permanent Magnet Synchronous Motor Based on Improved Fast Terminal Sliding Mode with Adaptive Control Law
Research on Speed Control of Permanent Magnet Synchronous Motor Based on Improved Fast Terminal Sliding Mode with Adaptive Control Law Open
Aiming at the control performance degradation of permanent magnet synchronous motor (PMSM) drive systems caused by uncertainties of internal and external disturbances, a robust control algorithm integrating an improved fast terminal slidin…
View article: SpectralX: Parameter-efficient Domain Generalization for Spectral Remote Sensing Foundation Models
SpectralX: Parameter-efficient Domain Generalization for Spectral Remote Sensing Foundation Models Open
Recent advances in Remote Sensing Foundation Models (RSFMs) have led to significant breakthroughs in the field. While many RSFMs have been pretrained with massive optical imagery, more multispectral/hyperspectral data remain lack of the co…
View article: ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models
ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models Open
Video understanding plays a vital role in bridging low-level visual signals with high-level cognitive reasoning, and is fundamental to applications such as autonomous driving, embodied AI, and the broader pursuit of AGI. The rapid developm…
View article: X-WebAgentBench: A Multilingual Interactive Web Benchmark for Evaluating Global Agentic System
X-WebAgentBench: A Multilingual Interactive Web Benchmark for Evaluating Global Agentic System Open
Recently, large language model (LLM)-based agents have achieved significant success in interactive environments, attracting significant academic and industrial attention. Despite these advancements, current research predominantly focuses o…
View article: Effects and mechanisms of a home-based action observation and motor imagery intervention on cognitive function and depression in spinal cord injury: a pilot randomized controlled trial protocol
Effects and mechanisms of a home-based action observation and motor imagery intervention on cognitive function and depression in spinal cord injury: a pilot randomized controlled trial protocol Open
Background Cognitive impairment and depression frequently occur after spinal cord injury (SCI) and adversely affect functional independence and quality of life. There is a lack of research in addressing this important area in SCI rehabilit…
View article: Multimodal Fusion Using Multi-View Domains for Data Heterogeneity in Federated Learning
Multimodal Fusion Using Multi-View Domains for Data Heterogeneity in Federated Learning Open
Multimodal information plays an important role in the advanced Internet of Things (IoT) in the era of 6G, which provides reliable and comprehensive assistance for downstream tasks through further fusion and analysis via federated learning …
View article: A Novel Azimuth Channel Errors Estimation Algorithm Based on Characteristic Clusters Statistical Treatment
A Novel Azimuth Channel Errors Estimation Algorithm Based on Characteristic Clusters Statistical Treatment Open
Azimuth multi-channel techniques show great promise in high-resolution, wide-swath synthetic aperture radar systems. However, in practical engineering applications, errors between channels can significantly affect the reconstruction of mul…
View article: A transient stability assessment method for power systems incorporating residual networks and BiGRU-attention
A transient stability assessment method for power systems incorporating residual networks and BiGRU-attention Open
View article: Assessment of the variability of unidirectional prepregs at multiple scales
Assessment of the variability of unidirectional prepregs at multiple scales Open
Understanding the microstructural variability in unidirectional composite prepreg tapes is relevant to investigating mechanisms of tape microstructure formation, their impact on its processability and the mechanical performance of the fina…
View article: Miniature FBG force sensor capable of effectively resisting lateral forces
Miniature FBG force sensor capable of effectively resisting lateral forces Open
This paper presents a high-precision miniature force sensor based on fiber Bragg grating (FBG) for measuring axial contact force (CF) between a medical instrument tip and tissue during minimally invasive surgery (MIS) palpation. The newly …
View article: Effect of Feature Size on Defects, Microstructure, and Mechanical Properties of Selective Laser Melted AlSi10Mg Lattice Structure
Effect of Feature Size on Defects, Microstructure, and Mechanical Properties of Selective Laser Melted AlSi10Mg Lattice Structure Open
Selective laser melting lightweight lattice structures have broad application prospects in the aerospace field. Understanding the dependence of mechanical performance on feature size is crucial for structure design. This work optimized the…
View article: Impact of PCV13 Vaccination on Pharyngeal Detection of <i>Streptococcus pneumoniae</i> Among Children — Suqian City, Jiangsu Province, China, February 2023–February 2025
Impact of PCV13 Vaccination on Pharyngeal Detection of <i>Streptococcus pneumoniae</i> Among Children — Suqian City, Jiangsu Province, China, February 2023–February 2025 Open
The PCV13 program successfully reduced pneumococcal detection rates, particularly among children who complete the 3-4 dose series. Continued surveillance of circulating S. pneumoniae serotypes is essential to monitor serotype replac…
View article: GeoFlowNet-SAR: Earthquake Displacement Estimation From Synthetic Aperture Radar Images
GeoFlowNet-SAR: Earthquake Displacement Estimation From Synthetic Aperture Radar Images Open
International audience
View article: X-WebAgentBench: A Multilingual Interactive Web Benchmark for Evaluating Global Agentic System
X-WebAgentBench: A Multilingual Interactive Web Benchmark for Evaluating Global Agentic System Open
View article: Base Station Link Optimization-Based Positioning Method in NLoS Propagation Environments
Base Station Link Optimization-Based Positioning Method in NLoS Propagation Environments Open
View article: Analysis and prediction of force characteristics of tubular turbine based on Hankel-DMD-LSTM
Analysis and prediction of force characteristics of tubular turbine based on Hankel-DMD-LSTM Open
In order to analyse and master the force characteristics of the prototype bulb turbine under critical cavitation condition, this study compared the force characteristics of the turbine under different operating conditions, and finally the …
View article: Machine learning modeling based on informer for predicting complex unsteady flow fields to reduce consumption of computational fluid dynamics simulation
Machine learning modeling based on informer for predicting complex unsteady flow fields to reduce consumption of computational fluid dynamics simulation Open
Accurately predicting the dynamic behaviour of complex flow fields has always been a major challenge in Computational Fluid Dynamics (CFD) research. This paper proposes an innovative approach based on the Informer model for efficient predi…
View article: Task-Parameter Nexus: Task-Specific Parameter Learning for Model-Based Control
Task-Parameter Nexus: Task-Specific Parameter Learning for Model-Based Control Open
This paper presents the Task-Parameter Nexus (TPN), a learning-based approach for online determination of the (near-)optimal control parameters of model-based controllers (MBCs) for tracking tasks. In TPN, a deep neural network is introduc…
View article: Neural Modulation Alteration to Positive and Negative Emotions in Depressed Patients: Insights from fMRI Using Positive/Negative Emotion Atlas
Neural Modulation Alteration to Positive and Negative Emotions in Depressed Patients: Insights from fMRI Using Positive/Negative Emotion Atlas Open
Background: Although it has been noticed that depressed patients show differences in processing emotions, the precise neural modulation mechanisms of positive and negative emotions remain elusive. FMRI is a cutting-edge medical imaging tec…
View article: STANet: A Novel Spatio-Temporal Aggregation Network for Depression Classification with Small and Unbalanced FMRI Data
STANet: A Novel Spatio-Temporal Aggregation Network for Depression Classification with Small and Unbalanced FMRI Data Open
Background: Early diagnosis of depression is crucial for effective treatment and suicide prevention. Traditional methods rely on self-report questionnaires and clinical assessments, lacking objective biomarkers. Combining functional magnet…
View article: A Spaceborne Passive Localization Algorithm Based on MSD-HOUGH for Multiple Signal Sources
A Spaceborne Passive Localization Algorithm Based on MSD-HOUGH for Multiple Signal Sources Open
Recently, the passive synthetic aperture (PSA) technique has been used in passive localization to improve the position accuracy of single source by estimating the Doppler parameter of the received signal. However, in the presence of multip…
View article: Fluctuation exponents of the half-space KPZ at stationarity
Fluctuation exponents of the half-space KPZ at stationarity Open
We study the half-space KPZ equation with a Neumann boundary condition, starting from stationary Brownian initial data. We derive a variance identity that links the fluctuations of the height function to the transversal fluctuations of a h…
View article: STANet: A Novel Spatio-Temporal Aggregation Network for Depression Classification with Small and Unbalanced FMRI Data
STANet: A Novel Spatio-Temporal Aggregation Network for Depression Classification with Small and Unbalanced FMRI Data Open
Accurate diagnosis of depression is crucial for timely implementation of optimal treatments, preventing complications and reducing the risk of suicide. Traditional methods rely on self-report questionnaires and clinical assessment, lacking…
View article: Super-Resolution for Land Surface Temperature Retrieval Images via Cross-Scale Diffusion Model Using Reference Images
Super-Resolution for Land Surface Temperature Retrieval Images via Cross-Scale Diffusion Model Using Reference Images Open
Geothermal resources are efficient, clean, and renewable energy sources. Using high-resolution images captured by remote sensing satellites for temperature retrieval and searching for geothermal anomaly areas is an efficient method. Howeve…
View article: Impact of Noisy Supervision in Foundation Model Learning
Impact of Noisy Supervision in Foundation Model Learning Open
Foundation models are usually pre-trained on large-scale datasets and then adapted to downstream tasks through tuning. However, the large-scale pre-training datasets, often inaccessible or too expensive to handle, can contain label noise t…
View article: Temporal convex combination‐based secure distributed estimation against cyberattacks and noisy input
Temporal convex combination‐based secure distributed estimation against cyberattacks and noisy input Open
This paper proposes a new secure distributed estimation for cyber‐physical systems against adversarial attacks with noisy input. To mitigate the effect of attacks, a novel distributed attack detection based on a reliable reference estimati…
View article: The Effects of Misinformation Identification in the Computer-mediated Communication Through Media Literacy Intervention
The Effects of Misinformation Identification in the Computer-mediated Communication Through Media Literacy Intervention Open
Computer-mediated communication is an integral form of recent communication that allows people to gain information quickly and improve the engagement of information. However, computer-mediated communication also provides a medium for misin…
View article: A Deep Reinforcement Active Learning Method for Multi-Label Image Classification
A Deep Reinforcement Active Learning Method for Multi-Label Image Classification Open
View article: Fractional Fourier-Based Frequency-Spatial–Spectral Prototype Network for Agricultural Hyperspectral Image Open-Set Classification
Fractional Fourier-Based Frequency-Spatial–Spectral Prototype Network for Agricultural Hyperspectral Image Open-Set Classification Open
At present, hyperspectral image classification (HSIC) technology has been warmly concerned in all walks of life, especially in agriculture. However, existing classification methods operate under the closed-set assumption, which deviates fr…