Yezheng Liu
YOU?
Author Swipe
View article: Pathology-CoT: Learning Visual Chain-of-Thought Agent from Expert Whole Slide Image Diagnosis Behavior
Pathology-CoT: Learning Visual Chain-of-Thought Agent from Expert Whole Slide Image Diagnosis Behavior Open
Diagnosing a whole-slide image is an interactive, multi-stage process of changing magnification and moving between fields. Although recent pathology foundation models demonstrated superior performances, practical agentic systems that decid…
View article: A co-evolving agentic AI system for medical imaging analysis
A co-evolving agentic AI system for medical imaging analysis Open
Agentic AI is rapidly advancing in healthcare and biomedical research. However, in medical image analysis, their performance and adoption remain limited due to the lack of a robust ecosystem, insufficient toolsets, and the absence of real-…
View article: Advances in the Biosynthetic Regulation and Functional Mechanisms of Glycine Betaine for Enhancing Plant Stress Resilience
Advances in the Biosynthetic Regulation and Functional Mechanisms of Glycine Betaine for Enhancing Plant Stress Resilience Open
Plants are frequently exposed to a range of abiotic stresses, including drought, salinity, extreme temperatures, and heavy metals, that severely impair their growth and productivity. Among the adaptive mechanisms that plants have evolved, …
View article: Enzymatic Stoichiometry and Driving Factors Under Different Land-Use Types in the Qinghai–Tibet Plateau Region
Enzymatic Stoichiometry and Driving Factors Under Different Land-Use Types in the Qinghai–Tibet Plateau Region Open
Eco-enzymatic stoichiometry provides a basis for understanding soil ecosystem functions, with implications for land management and ecological protection. Long-term climatic factors and human interferences have caused significant land-use t…
View article: The coherent two-phased process from sold online to redemption offline on an online daily-deal platform
The coherent two-phased process from sold online to redemption offline on an online daily-deal platform Open
View article: Developing a Framework for Online Review-Based Health Care Service Quality Assessment: Text-Mining Study
Developing a Framework for Online Review-Based Health Care Service Quality Assessment: Text-Mining Study Open
Background With the development of online health care platforms, patient reviews have become an important source for assessing medical service quality. However, the critical aspects of quality dimensions in textual reviews remain largely u…
View article: P485 – Enhancing prostate volume estimation: The role of artificial intelligence compared to conventional methods
P485 – Enhancing prostate volume estimation: The role of artificial intelligence compared to conventional methods Open
View article: ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images
ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images Open
Medical Visual Question Answering (Med-VQA) represents a critical and challenging subtask within the general VQA domain. Despite significant advancements in general VQA, multimodal large language models (MLLMs) still exhibit substantial li…
View article: Analysis of Factors Affecting the Water Inflow of Suspended Water Stop Curtain Foundation Pit Under Pressure Water Conditions
Analysis of Factors Affecting the Water Inflow of Suspended Water Stop Curtain Foundation Pit Under Pressure Water Conditions Open
View article: Identifying Useful Answers on Community-Based Question Answering Platforms: A Novel Unified Answer Comment-Based Approach
Identifying Useful Answers on Community-Based Question Answering Platforms: A Novel Unified Answer Comment-Based Approach Open
View article: Harnessing Machine Learning for the Sustainable Management of Surface Water in China: Identifying Key Driving Factors and Scenario Simulation
Harnessing Machine Learning for the Sustainable Management of Surface Water in China: Identifying Key Driving Factors and Scenario Simulation Open
View article: Impersonal in Chinese: A Syntactic Analysis of Existential Constructions
Impersonal in Chinese: A Syntactic Analysis of Existential Constructions Open
View article: Detecting Fake News on Social Media: A Novel Reliability Aware Machine-Crowd Hybrid Intelligence-Based Method
Detecting Fake News on Social Media: A Novel Reliability Aware Machine-Crowd Hybrid Intelligence-Based Method Open
Fake news on social media platforms poses a significant threat to societal systems, underscoring the urgent need for advanced detection methods. The existing detection methods can be divided into machine intelligence-based, crowd intellige…
View article: Towards Trustworthy Web Attack Detection: An Uncertainty-Aware Ensemble Deep Kernel Learning Model
Towards Trustworthy Web Attack Detection: An Uncertainty-Aware Ensemble Deep Kernel Learning Model Open
Web attacks are one of the major and most persistent forms of cyber threats, which bring huge costs and losses to web application-based businesses. Various detection methods, such as signature-based, machine learning-based, and deep learni…
View article: LLM-Enhanced Composed Image Retrieval: An Intent Uncertainty-Aware Linguistic-Visual Dual Channel Matching Model
LLM-Enhanced Composed Image Retrieval: An Intent Uncertainty-Aware Linguistic-Visual Dual Channel Matching Model Open
Composed image retrieval (CoIR) involves a multi-modal query of the reference image and modification text describing the desired changes, allowing users to express image retrieval intents flexibly and effectively. The key of CoIR lies in h…
View article: Towards Trustworthy Web Attack Detection: An Uncertainty-Aware Ensemble Deep Kernel Learning Model
Towards Trustworthy Web Attack Detection: An Uncertainty-Aware Ensemble Deep Kernel Learning Model Open
View article: A Bayesian deep recommender system for uncertainty-aware online physician recommendation
A Bayesian deep recommender system for uncertainty-aware online physician recommendation Open
View article: Research on Mainstream Media News Practice from the Perspective of Media Fusion-- Taking the New Beijing News as an Example
Research on Mainstream Media News Practice from the Perspective of Media Fusion-- Taking the New Beijing News as an Example Open
As the wave of media integration approaches, how mainstream media can adapt to the trend of the times and achieve the transition from traditional single reporting forms to diverse and integrated forms of news reporting in new media, and ho…
View article: A Whole-Process Certifiably Robust Aggregation Method Against Backdoor Attacks in Federated Learning
A Whole-Process Certifiably Robust Aggregation Method Against Backdoor Attacks in Federated Learning Open
Federated Learning (FL) has garnered widespread adoption across various domains such as finance, healthcare, and cybersecurity. Nonetheless, FL remains under significant threat from backdoor attacks, wherein malicious actors insert trigger…
View article: Emotion-aware Personalized Music Recommendation with a Heterogeneity-aware Deep Bayesian Network
Emotion-aware Personalized Music Recommendation with a Heterogeneity-aware Deep Bayesian Network Open
Music recommender systems play a critical role in music streaming platforms by providing users with music that they are likely to enjoy. Recent studies have shown that user emotions can influence users' preferences for music moods. However…
View article: Identifying Useful Answers on Community-Based Question Answering Platforms: A Novel Unified Answer Comment-Based Approach
Identifying Useful Answers on Community-Based Question Answering Platforms: A Novel Unified Answer Comment-Based Approach Open
View article: Understanding Information Sensitivity Perceptions and its Impact on Information Privacy Concerns in E-Commerce Services: Insights from China
Understanding Information Sensitivity Perceptions and its Impact on Information Privacy Concerns in E-Commerce Services: Insights from China Open
View article: Health IT in our daily life: impact of mobile phone use on the emotions and compliance of diabetes patients
Health IT in our daily life: impact of mobile phone use on the emotions and compliance of diabetes patients Open
Purpose Leveraging information technology (IT) to improve the treatment and support of patients is a widely studied topic in healthcare. For chronic diseases, such as diabetes, the use of information technology is even more important since…
View article: Next Location Recommendation: A Multi-context Features Integration Perspective
Next Location Recommendation: A Multi-context Features Integration Perspective Open
Next location recommendation aims to mine users’ historical trajectories to predict their potentially preferred locations in the next moment. Although previous studies have explored the idea of incorporating location or social contextual i…
View article: Additive Feature Attribution Explainable Methods to Craft Adversarial Attacks for Text Classification and Text Regression
Additive Feature Attribution Explainable Methods to Craft Adversarial Attacks for Text Classification and Text Regression Open
Deep learning (DL) models have significantly improved the performance of text classification and text regression tasks. However, DL models are often strikingly vulnerable to adversarial attacks. Many researchers have aimed to develop adve…
View article: Local Post-hoc Explainable Methods for Adversarial Text Attacks
Local Post-hoc Explainable Methods for Adversarial Text Attacks Open
Deep learning models have significantly advanced various natural language processing tasks. However, they are strikingly vulnerable to adversarial text attacks, even in the black-box setting where no model knowledge is accessible to hacker…
View article: Additive Feature Attribution Explainable Methods to Craft Adversarial Attacks for Text Classification and Text Regression
Additive Feature Attribution Explainable Methods to Craft Adversarial Attacks for Text Classification and Text Regression Open
Deep learning (DL) models have significantly improved the performance of text classification and text regression tasks. However, DL models are often strikingly vulnerable to adversarial attacks. Many researchers have aimed to develop adve…
View article: Toward a research framework to conceptualize data as a factor of production: The data marketplace perspective
Toward a research framework to conceptualize data as a factor of production: The data marketplace perspective Open
The widespread use of machine learning techniques and artificial intelligence algorithms has highlighted the strategic role of data. To acquire data for training algorithms and eventually empowering the digital transformation, data marketp…
View article: Annual Water Consumption Forecast of Hefei Based on ARIMA Model
Annual Water Consumption Forecast of Hefei Based on ARIMA Model Open
The ARIMA entity model was used in Hefei's current water demand coding sequence from 1990 to 2018. According to the ADF (Unit Root Test), it is clear that the number of differences d in the entity model is 2, and the main parameters in the…
View article: The impact of imitation on Chinese social commerce buyers’ purchase behavior: The moderating role of uncertainty
The impact of imitation on Chinese social commerce buyers’ purchase behavior: The moderating role of uncertainty Open