Yongting Zhang
YOU?
Author Swipe
View article: LiveSearchBench: An Automatically Constructed Benchmark for Retrieval and Reasoning over Dynamic Knowledge
LiveSearchBench: An Automatically Constructed Benchmark for Retrieval and Reasoning over Dynamic Knowledge Open
Evaluating large language models (LLMs) on question answering often relies on static benchmarks that reward memorization and understate the role of retrieval, failing to capture the dynamic nature of world knowledge. We present LiveSearchB…
View article: Chromosome-level genome assembly of Myristica yunnanensis sheds light on genomic limitations underlying its critically endangered status in China
Chromosome-level genome assembly of Myristica yunnanensis sheds light on genomic limitations underlying its critically endangered status in China Open
View article: Advances in Synthesis and Ignition Performance of Ionic Liquid–Hydrogen Peroxide Green Propellants
Advances in Synthesis and Ignition Performance of Ionic Liquid–Hydrogen Peroxide Green Propellants Open
The ionic liquid–hydrogen peroxide propellant system has emerged as a promising green propellant candidate, synergistically combining the unique advantages of ionic liquids (such as negligible vapor pressure, low melting points, high therm…
View article: SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model
SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model Open
The emergence of Vision Language Models (VLMs) has brought unprecedented advances in understanding multimodal information. The combination of textual and visual semantics in VLMs is highly complex and diverse, making the safety alignment o…
View article: Assessment of Multimodal Large Language Models in Alignment with Human Values
Assessment of Multimodal Large Language Models in Alignment with Human Values Open
Large Language Models (LLMs) aim to serve as versatile assistants aligned with human values, as defined by the principles of being helpful, honest, and harmless (hhh). However, in terms of Multimodal Large Language Models (MLLMs), despite …
View article: From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities
From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities Open
Multi-modal Large Language Models (MLLMs) have shown impressive abilities in generating reasonable responses with respect to multi-modal contents. However, there is still a wide gap between the performance of recent MLLM-based applications…
View article: PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety
PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety Open
Multi-agent systems, when enhanced with Large Language Models (LLMs), exhibit profound capabilities in collective intelligence. However, the potential misuse of this intelligence for malicious purposes presents significant risks. To date, …
View article: Author Correction: Chromosome-level genomes of three key Allium crops and their trait evolution
Author Correction: Chromosome-level genomes of three key Allium crops and their trait evolution Open
View article: An Intelligent Mental Health Identification Method for College Students: A Mixed-Method Study
An Intelligent Mental Health Identification Method for College Students: A Mixed-Method Study Open
Purpose: Mental health assessments that combine patients’ facial expressions and behaviors have been proven effective, but screening large-scale student populations for mental health problems is time-consuming and labor-intensive. This stu…
View article: Thirteen Dipterocarpoideae genomes provide insights into their evolution and borneol biosynthesis
Thirteen Dipterocarpoideae genomes provide insights into their evolution and borneol biosynthesis Open
View article: A secure visual framework for multi-index protection evaluation in networks
A secure visual framework for multi-index protection evaluation in networks Open
Mining the core value of Industrial Internet of Things (IIoT) data safely and reducing the risk of malicious attacks are the inherent requirements of industrial data visualization. Visualization technology has become the main tool for data…
View article: A differential privacy protection query language for medical data: a proof-of-concept system validation
A differential privacy protection query language for medical data: a proof-of-concept system validation Open
Objective: Medical data mining and sharing is an important process in E-Health applications. However, because these data consist of a large amount of personal private information of patients, there is the risk of privacy disclosure when sh…
View article: Training Spiking Neural Networks with Accumulated Spiking Flow
Training Spiking Neural Networks with Accumulated Spiking Flow Open
The fast development of neuromorphic hardwares promotes Spiking Neural Networks (SNNs) to a thrilling research avenue. Current SNNs, though much efficient, are less effective compared with leading Artificial Neural Networks (ANNs) especial…
View article: A Clonal Selection Optimization System for Multiparty Secure Computing
A Clonal Selection Optimization System for Multiparty Secure Computing Open
The innovation of the deep learning modeling scheme plays an important role in promoting the research of complex problems handled with artificial intelligence in smart cities and the development of the next generation of information techno…
View article: A Differential Privacy Protection Query Language for Medical Data: Study Design (Preprint)
A Differential Privacy Protection Query Language for Medical Data: Study Design (Preprint) Open
BACKGROUND Medical data mining and sharing is an important process to realize the value of medical big data in E-Health applications. However, medical data contains a large amount of personal private information of patients, there is a ri…