Yu Zhang
YOU?
Author Swipe
View article: Research Hotspots and Emerging Trends of Schizophrenia and Immune Response: A Bibliometric Analysis
Research Hotspots and Emerging Trends of Schizophrenia and Immune Response: A Bibliometric Analysis Open
Introduction Schizophrenia is a complex psychiatric disorder increasingly recognized for its association with immune responses. This bibliometric analysis aims to systematically evaluate global research trends, emerging themes, and collabo…
View article: Underwater Image Enhancement with a Hybrid U-Net-Transformer and Recurrent Multi-Scale Modulation
Underwater Image Enhancement with a Hybrid U-Net-Transformer and Recurrent Multi-Scale Modulation Open
The quality of underwater imagery is inherently degraded by light absorption and scattering, a challenge that severely limits its application in critical domains such as marine robotics and archeology. While existing enhancement methods, i…
View article: Real-Time Lightweight Vehicle Object Detection via Layer-Adaptive Model Pruning
Real-Time Lightweight Vehicle Object Detection via Layer-Adaptive Model Pruning Open
With the rapid advancement in autonomous driving technology, vehicle object detection has become a crucial component of perception systems, where accuracy and inference speed directly influence driving safety. To address the limitations of…
View article: Beyond Instance Consistency: Investigating View Diversity in Self-supervised Learning
Beyond Instance Consistency: Investigating View Diversity in Self-supervised Learning Open
Self-supervised learning (SSL) conventionally relies on the instance consistency paradigm, assuming that different views of the same image can be treated as positive pairs. However, this assumption breaks down for non-iconic data, where di…
View article: Conan: A Chunkwise Online Network for Zero-Shot Adaptive Voice Conversion
Conan: A Chunkwise Online Network for Zero-Shot Adaptive Voice Conversion Open
Zero-shot online voice conversion (VC) holds significant promise for real-time communications and entertainment. However, current VC models struggle to preserve semantic fidelity under real-time constraints, deliver natural-sounding conver…
View article: Research and simulation analysis of Jack based dental treatment chair human–machine system
Research and simulation analysis of Jack based dental treatment chair human–machine system Open
With the continuous changes in people's dietary habits, oral health issues have become a growing concern. As an essential device in the dental treatment process, the rationality and comfort of dental treatment chairs have become a focal po…
View article: Reasoning-Aligned Perception Decoupling for Scalable Multi-modal Reasoning
Reasoning-Aligned Perception Decoupling for Scalable Multi-modal Reasoning Open
Recent breakthroughs in reasoning language models have significantly advanced text-based reasoning. On the other hand, Multi-modal Large Language Models (MLLMs) still lag behind, hindered by their outdated internal LLMs. Upgrading these is…
View article: Clinical metabolomics reveals potential diagnostic biomarkers in serum samples from patients with generalized ligamentous laxity
Clinical metabolomics reveals potential diagnostic biomarkers in serum samples from patients with generalized ligamentous laxity Open
Objectives Discovering the potential metabolic alterations underlying generalized ligamentous laxity (GLL) is crucial for identifying new therapeutic targets and improving patient prognosis. Serum metabolites could mirror systemic and loca…
View article: Sampling of Graph Signals Based on Joint Time-Vertex Fractional Fourier Transform
Sampling of Graph Signals Based on Joint Time-Vertex Fractional Fourier Transform Open
With the growing demand for non-Euclidean data analysis, graph signal processing (GSP) has gained significant attention for its capability to handle complex time-varying data. This paper introduces a novel sampling method based on the join…
View article: FLASH: Latent-Aware Semi-Autoregressive Speculative Decoding for Multimodal Tasks
FLASH: Latent-Aware Semi-Autoregressive Speculative Decoding for Multimodal Tasks Open
Large language and multimodal models (LLMs and LMMs) exhibit strong inference capabilities but are often limited by slow decoding speeds. This challenge is especially acute in LMMs, where visual inputs typically comprise more tokens with l…
View article: Loschmidt echo zeros and dynamical quantum phase transitions in finite-size quantum systems with linear quench
Loschmidt echo zeros and dynamical quantum phase transitions in finite-size quantum systems with linear quench Open
Dynamical quantum phase transitions reveal singularities in quench dynamics, characterized by the emergence of Loschmidt echo zeros at critical times, which usually exist only in the thermodynamical limit but are absent in finite size quan…
View article: Recent advances in the role of polysaccharides in liver diseases: a review
Recent advances in the role of polysaccharides in liver diseases: a review Open
Liver diseases are a serious health problem worldwide, especially with a sustained increase in the burden of it every year. However, drugs commonly used in patients have limited efficacy and serious adverse reactions associated with long-t…
View article: Toward Accurate Weight-based Measurement and Periodic Edge Measurement in Graph Stream
Toward Accurate Weight-based Measurement and Periodic Edge Measurement in Graph Stream Open
Graph streams of sequentially arriving edges are commonly used to represent complex structured data in interactive networks. Typically, graph streams are extremely large and high-velocity. Existing schemes by using graph sketch for summari…
View article: Improving Scientific Document Retrieval with Concept Coverage-based Query Set Generation
Improving Scientific Document Retrieval with Concept Coverage-based Query Set Generation Open
In specialized fields like the scientific domain, constructing large-scale human-annotated datasets poses a significant challenge due to the need for domain expertise. Recent methods have employed large language models to generate syntheti…
View article: Diffusion Models for Computational Neuroimaging: A Survey
Diffusion Models for Computational Neuroimaging: A Survey Open
Computational neuroimaging involves analyzing brain images or signals to provide mechanistic insights and predictive tools for human cognition and behavior. While diffusion models have shown stability and high-quality generation in natural…
View article: Application of Artificial Intelligence In Drug-target Interactions Prediction: A Review
Application of Artificial Intelligence In Drug-target Interactions Prediction: A Review Open
Predicting drug-target interactions (DTI) is a complex task. With the introduction of artificial intelligence (AI) methods such as machine learning and deep learning, AI-based DTI prediction can significantly enhance speed, reduce costs, a…
View article: TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis
TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis Open
Customizable multilingual zero-shot singing voice synthesis (SVS) has various potential applications in music composition and short video dubbing. However, existing SVS models overly depend on phoneme and note boundary annotations, limitin…
View article: ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model
ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model Open
Visual object tracking aims to locate a targeted object in a video sequence based on an initial bounding box. Recently, Vision-Language~(VL) trackers have proposed to utilize additional natural language descriptions to enhance versatility …
View article: Elucidating the neuropathological and molecular heterogeneity of amyloid-beta and tau in Alzheimer's disease through machine learning and transcriptomic integration
Elucidating the neuropathological and molecular heterogeneity of amyloid-beta and tau in Alzheimer's disease through machine learning and transcriptomic integration Open
Discerning functional brain network variations related to neuropathological aggregates in Alzheimer's disease (AD), including amyloid-beta (Abeta) and phosphorylated tau (p-tau), is crucial for understanding their link to cognitive decline…
View article: EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions
EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions Open
GPT-4o, an omni-modal model that enables vocal conversations with diverse emotions and tones, marks a milestone for omni-modal foundation models. However, empowering Large Language Models to perceive and generate images, texts, and speeche…
View article: TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control
TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control Open
Zero-shot singing voice synthesis (SVS) with style transfer and style control aims to generate high-quality singing voices with unseen timbres and styles (including singing method, emotion, rhythm, technique, and pronunciation) from audio …
View article: Enhancing Sharpness-Aware Minimization by Learning Perturbation Radius
Enhancing Sharpness-Aware Minimization by Learning Perturbation Radius Open
Sharpness-aware minimization (SAM) is to improve model generalization by searching for flat minima in the loss landscape. The SAM update consists of one step for computing the perturbation and the other for computing the update gradient. W…
View article: Construction of effective reproduction number of infectious disease individuals based on spatiotemporal discriminant search model: take hand-foot-mouth disease as an example
Construction of effective reproduction number of infectious disease individuals based on spatiotemporal discriminant search model: take hand-foot-mouth disease as an example Open
The model comprehensively considers both temporal variation and spatial heterogeneity in disease transmission and accounts for each individual's distinct time of onset and spatial location. This proposed method differs significantly from e…
View article: A transformer-based multi-task deep learning model for simultaneous T-stage identification and segmentation of nasopharyngeal carcinoma
A transformer-based multi-task deep learning model for simultaneous T-stage identification and segmentation of nasopharyngeal carcinoma Open
Background Accurate tumor target contouring and T staging are vital for precision radiation therapy in nasopharyngeal carcinoma (NPC). Identifying T-stage and contouring the Gross tumor volume (GTV) manually is a laborious and highly time-…
View article: Under the Vision of Situated Learning: Analysing the Influence of Educational Video Games on English Vocabulary Retention in Chinese Childrens Second Language Acquisition
Under the Vision of Situated Learning: Analysing the Influence of Educational Video Games on English Vocabulary Retention in Chinese Childrens Second Language Acquisition Open
This study will analyze the influence of educational video games on English vocabulary retention in Chinese childrens second language acquisition. This study base on the situated learning theory and the ABC reading which is both mobile and…
View article: Multi-Task Learning in Natural Language Processing: An Overview
Multi-Task Learning in Natural Language Processing: An Overview Open
Deep learning approaches have achieved great success in the field of Natural Language Processing (NLP). However, directly training deep neural models often suffer from overfitting and data scarcity problems that are pervasive in NLP tasks.…
View article: A Distributed Scalable Cross-chain State Channel Scheme Based on Recursive State Synchronization
A Distributed Scalable Cross-chain State Channel Scheme Based on Recursive State Synchronization Open
As cross-chain technology continues to advance, the scale of cross-chain transactions is experiencing significant expansion. To improve scalability, researchers have turned to the study of cross-chain state channels. However, most of the e…
View article: StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis
StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis Open
Style transfer for out-of-domain (OOD) singing voice synthesis (SVS) focuses on generating high-quality singing voices with unseen styles (such as timbre, emotion, pronunciation, and articulation skills) derived from reference singing voic…
View article: Atypical varicella-zoster virus meningitis in a young immunocompetent adult during enterovirus epidemic season: A case report and literature review
Atypical varicella-zoster virus meningitis in a young immunocompetent adult during enterovirus epidemic season: A case report and literature review Open
Background Varicella-zoster virus (VZV) can cause acute brain infection manifesting as meningitis or encephalitis, which more likely occurs in winter and population with immunocompromised conditions[1]. During the enterovirus epidemic seas…