Yue Gao
YOU?
Author Swipe
View article: A Novel Strategy for Soft Tissue Sarcoma Lattice Radiotherapy: Integrating X-Ray andγ-Ray Technologies to Optimize Dose Delivery
A Novel Strategy for Soft Tissue Sarcoma Lattice Radiotherapy: Integrating X-Ray andγ-Ray Technologies to Optimize Dose Delivery Open
Background: The TaiChi radiotherapy platform is an innovative system integrating linear accelerator (LINAC) and Gamma Knife technologies, approved by both NMPA and FDA. This hybrid design enables bimodal (X-ray and γ-ray) radiation deliver…
View article: Integration of X-Ray and γ-Ray technologies in lattice radiotherapy: a novel approach for optimizing dose delivery in large-volume non-small cell lung cancer
Integration of X-Ray and γ-Ray technologies in lattice radiotherapy: a novel approach for optimizing dose delivery in large-volume non-small cell lung cancer Open
By integrating X-ray and γ-ray technologies, this platform enhances the vertex dose within the GTV while reducing doses to the GTV margins and OARs, offering a promising and feasible approach for the treatment of LRT in patients with large…
View article: FineSkiing: A Fine-grained Benchmark for Skiing Action Quality Assessment
FineSkiing: A Fine-grained Benchmark for Skiing Action Quality Assessment Open
Action Quality Assessment (AQA) aims to evaluate and score sports actions, which has attracted widespread interest in recent years. Existing AQA methods primarily predict scores based on features extracted from the entire video, resulting …
View article: A Tutorial on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guide
A Tutorial on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guide Open
View article: Changes in keystone species attenuate the complexity and stability of soil microbial networks during alpine meadow degradation
Changes in keystone species attenuate the complexity and stability of soil microbial networks during alpine meadow degradation Open
In recent years, intensified human activities and climate change have led to the significant degradation of grasslands worldwide. Soil microbial network structure and function are crucial indicators of grassland degradation. Understanding …
View article: Large language models management of medications: three performance analyses
Large language models management of medications: three performance analyses Open
Purpose: Large language models (LLMs) have proven performance for certain diagnostic tasks, however limited studies have evaluated their consistency in recommending appropriate medication regimens for a given diagnosis. Medication manageme…
View article: FLASH radiotherapy at a crossroads: a bibliometric perspective on progress and challenges
FLASH radiotherapy at a crossroads: a bibliometric perspective on progress and challenges Open
View article: Metformin on the Presence of COVID-19 Symptoms Over 6 Months: The ACTIV-6 Randomized Clinical Trial
Metformin on the Presence of COVID-19 Symptoms Over 6 Months: The ACTIV-6 Randomized Clinical Trial Open
Background: The effect of metformin on preventing long-term COVID-19 symptoms among low-risk adults has not been studied. The objective of this study was to Assess metformin compared with placebo during acute SARS-CoV-2 infection on the pr…
View article: Patient rights and consent form language about intraoperative audiovisual recording
Patient rights and consent form language about intraoperative audiovisual recording Open
Background Intraoperative audiovisual recordings offer benefits in quality improvement, education, and research, but challenges hinder their routine use. No comprehensive guidelines exist on how intraoperative recordings should be communic…
View article: Diff$^2$I2P: Differentiable Image-to-Point Cloud Registration with Diffusion Prior
Diff$^2$I2P: Differentiable Image-to-Point Cloud Registration with Diffusion Prior Open
Learning cross-modal correspondences is essential for image-to-point cloud (I2P) registration. Existing methods achieve this mostly by utilizing metric learning to enforce feature alignment across modalities, disregarding the inherent moda…
View article: Solvent-free thermoplastic foaming for superelastic graphene monoliths
Solvent-free thermoplastic foaming for superelastic graphene monoliths Open
View article: Addressing Challenges in Educating ESL Learners with Autism: Reviewing Effective Strategies for Language Acquisition
Addressing Challenges in Educating ESL Learners with Autism: Reviewing Effective Strategies for Language Acquisition Open
Language acquisition presents unique challenges to students with Autism Spectrum Disorder (ASD) who are learning English as a Second Language (ESL). This paper aims to review studies examining the intersection between ASD and ESL, focusing…
View article: Uncovering Hidden Violent Tendencies in LLMs: A Demographic Analysis via Behavioral Vignettes
Uncovering Hidden Violent Tendencies in LLMs: A Demographic Analysis via Behavioral Vignettes Open
Large language models (LLMs) are increasingly proposed for detecting and responding to violent content online, yet their ability to reason about morally ambiguous, real-world scenarios remains underexamined. We present the first study to e…
View article: Memory-Augmented Incomplete Multimodal Survival Prediction via Cross-Slide and Gene-Attentive Hypergraph Learning
Memory-Augmented Incomplete Multimodal Survival Prediction via Cross-Slide and Gene-Attentive Hypergraph Learning Open
Multimodal pathology-genomic analysis is critical for cancer survival prediction. However, existing approaches predominantly integrate formalin-fixed paraffin-embedded (FFPE) slides with genomic data, while neglecting the availability of o…
View article: Deep learning for automated grading of radiographic sacroiliitis
Deep learning for automated grading of radiographic sacroiliitis Open
The AI model demonstrated high diagnostic accuracy and can greatly enhance the precision of radiographic sacroiliitis grading.
View article: SoftHGNN: Soft Hypergraph Neural Networks for General Visual Recognition
SoftHGNN: Soft Hypergraph Neural Networks for General Visual Recognition Open
Visual recognition relies on understanding both the semantics of image tokens and the complex interactions among them. Mainstream self-attention methods, while effective at modeling global pair-wise relations, fail to capture high-order as…
View article: Hyper-RAG: Combating LLM Hallucinations Using Hypergraph-Driven Retrieval-Augmented Generation
Hyper-RAG: Combating LLM Hallucinations Using Hypergraph-Driven Retrieval-Augmented Generation Open
Large language models (LLMs) have transformed various sectors, including education, finance, and medicine, by enhancing content generation and decision-making processes. However, their integration into the medical field is cautious due to …
View article: Protein succinylome analysis identifies citrate synthase as a central regulator of osteoclast metabolic activity
Protein succinylome analysis identifies citrate synthase as a central regulator of osteoclast metabolic activity Open
Tumour necrosis factor ligand superfamily member 11 (TNFSF11; RANKL) and macrophage colony‐stimulating factor 1 receptor (M‐CSF) differentiate macrophages into osteoclasts. This process is characterised by changes in metabolic activity tha…
View article: Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generation
Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generation Open
Large language models (LLMs) have transformed various sectors, including education, finance, and medicine, by enhancing content generation and decision-making processes. However, their integration into the medical field is cautious due to …
View article: Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks
Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks Open
View article: Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks
Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks Open
Deep reinforcement learning (DRL) has emerged as a promising approach for robotic control, but its realworld deployment remains challenging due to its vulnerability to environmental perturbations. Existing white-box adversarial attack meth…
View article: Neural-Polyptych: Content Controllable Painting Recreation for Diverse Genres
Neural-Polyptych: Content Controllable Painting Recreation for Diverse Genres Open
View article: ERetinex: Event Camera Meets Retinex Theory for Low-Light Image Enhancement
ERetinex: Event Camera Meets Retinex Theory for Low-Light Image Enhancement Open
Low-light image enhancement aims to restore the under-exposure image captured in dark scenarios. Under such scenarios, traditional frame-based cameras may fail to capture the structure and color information due to the exposure time limitat…
View article: Hypergraph Foundation Model
Hypergraph Foundation Model Open
Hypergraph neural networks (HGNNs) effectively model complex high-order relationships in domains like protein interactions and social networks by connecting multiple vertices through hyperedges, enhancing modeling capabilities, and reducin…
View article: Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective
Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective Open
Deep Reinforcement Learning (DRL) suffers from uncertainties and inaccuracies in the observation signal in realworld applications. Adversarial attack is an effective method for evaluating the robustness of DRL agents. However, existing att…
View article: LEO-Split: A Semi-Supervised Split Learning Framework over LEO Satellite Networks
LEO-Split: A Semi-Supervised Split Learning Framework over LEO Satellite Networks Open
Recently, the increasing deployment of LEO satellite systems has enabled various space analytics (e.g., crop and climate monitoring), which heavily relies on the advancements in deep learning (DL). However, the intermittent connectivity be…
View article: Shifting-Merging: Secure, High-Capacity and Efficient Steganography via Large Language Models
Shifting-Merging: Secure, High-Capacity and Efficient Steganography via Large Language Models Open
In the face of escalating surveillance and censorship within the cyberspace, the sanctity of personal privacy has come under siege, necessitating the development of steganography, which offers a way to securely hide messages within innocen…
View article: Inbound Innovation in Content Marketing: Brand Stories in Social Media
Inbound Innovation in Content Marketing: Brand Stories in Social Media Open
View article: Visual Analysis of Urban Design and Planning Based on Virtual Reality Technology
Visual Analysis of Urban Design and Planning Based on Virtual Reality Technology Open
View article: A semi-automatic annotation method for instance segmentation datasets of industrial objects
A semi-automatic annotation method for instance segmentation datasets of industrial objects Open