Explanipedia

Video-QTR: Query-Driven Temporal Reasoning Framework for Lightweight Video Understanding Open

Xinkui Zhao, Zuxin Wang, Yifan Zhang, Guanjie Cheng, Yueshen Xu , et al. · 2025

The rapid development of multimodal large-language models (MLLMs) has significantly expanded the scope of visual language reasoning, enabling unified systems to interpret and describe complex visual content. However, applying these models …

Completion by Comprehension: Guiding Code Generation with Multi-Granularity Understanding Open

Xinkui Zhao, R. Liu, Yifan Zhang, Zhi Chen, Lei Zhang , et al. · 2025

As code completion task from function-level to repository-level, leveraging contextual information from large-scale codebases becomes a core challenge. However, existing retrieval-augmented generation (RAG) methods typically treat code as …

Vegapunk: Accurate and Fast Decoding for Quantum LDPC Codes with Online Hierarchical Algorithm and Sparse Accelerator Open

Kai Zhou, Liqiang Lu, Debin Xiang, Chunhui Tao, Anbang Wu , et al. · 2025

Biomechanical design of titanium-PEEK combined fusion cage based on PLIF surgical model Open

Chunsheng Liu, Yutang Xie, Xinrui Wu, Yanqin Wang, Yanru Xue , et al. · 2025

Fusion devices play a critical role in lumbar fusion surgery. Titanium alloy fusion devices offer good biocompatibility and stability, but their mechanical properties far exceed those of bone, leading to stress shielding effects after impl…

Preguss: It Analyzes, It Specifies, It Verifies Open

Z Y Wang, T.-H. Jonah Lin, Mingshuai Chen, Mingqi Yang, Haokun Li , et al. · 2025

A Green Paper on AI, Data Governance, and Metadata Policies for Europe's Music Ecosystem Open

Wei Ni, Xiaoye Miao, Xiangyu Zhao, Yangyang Wu, Jianwei Yin · 2025

This Green Paper is a maturing policy document developed within the Open Music Europe (OpenMusE) Horizon Europe Research and Innovation Action (Grant Agreement No. 101095295). It deliberately combines policy research with implementation pi…

Agentic Services Computing Open

Shuiguang Deng, Hailiang Zhao, Ziqi Wang, Guanjie Cheng, Peng Chen , et al. · 2025

The rise of large language model (LLM)-powered agents is transforming services computing, moving it beyond static, request-driven functions toward dynamic, goal-oriented, and socially embedded multi-agent ecosystems. We propose Agentic Ser…

Revisiting Vulnerability Patch Localization: An Empirical Study and LLM-Based Solution Open

Haoran Xu, Zhi Chen, Junxiao Han, Xinkui Zhao, Jianwei Yin , et al. · 2025

Open-source software vulnerability patch detection is a critical component for maintaining software security and ensuring software supply chain integrity. Traditional manual detection methods face significant scalability challenges when pr…

CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing Open

Boyu Zhang, Ping He, Xuhong Zhang, Yun Lei, Jianwei Yin · 2025

With the widespread adoption of open-source code language models (code LMs), intellectual property (IP) protection has become an increasingly critical concern. While current watermarking techniques have the potential to identify the code L…

GRACE: Graph-Guided Repository-Aware Code Completion through Hierarchical Code Fusion Open

Xingliang Wang, Baoyi Wang, Zhi Chen, Junxiao Han, Xinkui Zhao , et al. · 2025

LLMs excel in localized code completion but struggle with repository-level tasks due to limited context windows and complex semantic and structural dependencies across codebases. While Retrieval-Augmented Generation (RAG) mitigates context…

Job Tenure and Gendered Perception of Workplace Challenges in Gendered Organizations: Computer Science, Engineering, and Mathematics Fields Open

Jisu Park, Sarah Damaske, Jiwon Choi, Susan M. McHale, Joshua G. Rosenberger , et al. · 2025

The authors examine the gendered perceptions of workplace challenges in the male-dominated fields of computer science, engineering, and mathematics (CSEM). Using novel qualitative and quantitative data from an online survey of 3,556 cisgen…

BPI: A Novel Efficient and Reliable Search Structure for Hybrid Storage Blockchain Open

Xinkui Zhao, Rong Xiong, Guanjie Cheng, Xiaolong Jin, Shawn Shi , et al. · 2025

Hybrid storage solutions have emerged as potent strategies to alleviate the data storage bottlenecks prevalent in blockchain systems. These solutions harness off-chain Storage Services Providers (SPs) in conjunction with Authenticated Data…

Optimization of braided stent design for cerebral aneurysms: the role of wire cross-sectional geometry Open

Aohua Zhang, Xinru Li, Zhengbiao Yang, Yutang Xie, Tao Wu , et al. · 2025

Flow-diverting stents are crucial for aneurysm treatment, with their structural design significantly impacting post-implantation hemodynamics. While clinically effective, opportunities remain to enhance their flexibility, flow diversion ca…

Modality-Aware Diffusion Augmentation with Consistent Subspace Disentanglement for Session-based Recommendation Open

Jiajie Su, Chaochao Chen, Weiming Liu, Yuhang Wang, Yihao Wang , et al. · 2025

A Robust Incomplete Multimodal Low-Rank Adaptation Approach for Emotion Recognition Open

Xinkui Zhao, J. Shu, Yangyang Wu, Guanjie Cheng, Z. Q. Liu , et al. · 2025

Multimodal Emotion Recognition (MER) often encounters incomplete multimodality in practical applications due to sensor failures or privacy protection requirements. While existing methods attempt to address various incomplete multimodal sce…

General Neural Embedding for Sequence Distance Approximation Open

Zhihao Chang, Ding Wang, Xiu Tang, Kingsum Chow, Jianwei Yin · 2025

Fairness-Aware Classification over Incomplete Data Open

Xiaoye Miao, Lei Qiang, Guilin Huang, Yangyang Wu, Jianwei Yin · 2025

Parf: An Adaptive Abstraction-Strategy Tuner for Static Analysis Open

Z Y Wang, M.C. Chen, T.-H. Jonah Lin, Linyu Yang, Jun-Hao Zhuo , et al. · 2025

LLMAppHub: A Large Collection of LLM-based Applications for the Research Community Open

Zhaoyang Wu, Chen Zhi, Junxiao Han, Shuiguang Deng, Jianwei Yin · 2025

ARTERY: Fast Quantum Feedback using Branch Prediction Open

Wuwei Tian, Liqiang Lu, Siwei Tan, Yun Liang, Tingting Li , et al. · 2025

Qtenon: Towards Low-Latency Architecture Integration for Accelerating Hybrid Quantum-Classical Computing Open

Chunhui Tao, Liqiang Lu, Size Zheng, Li‐Wen Chang, Minghua Shen , et al. · 2025

Comparison of bronchoalveolar lavage fluid mNGS and sputum culture in the clinical application of severe pneumonia Open

Na Gao, Jianwei Yin, Na Niu, Wendong Hao, Xiushan Chen , et al. · 2025

Objective The purpose of this study is to compare the clinical application value of bronchoalveolar lavage fluid (BALF) mNGS and sputum culture in severe pulmonary infections, and to provide guidance for clinicians in selecting the appropr…

403 | A SINGLE‐ARM, MULTI‐CENTER, OBSERVATIONAL STUDY OF SELINEXOR COMBINED BORTEZOMIB, LENALIDOMIDE, AND DEXAMETHASONE IN HIGH‐RISK NEWLY DIAGNOSED MULTIPLE MYELOMA Open

Jianwei Yin, Haiyan Wu, Xin Zhou, X. Li, Yuan Chen , et al. · 2025

Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks Open

Yinghui Bao, Xuhong Zhang, Tianyu Du, Xinkui Zhao, Z. Y. Feng , et al. · 2025

Large language models (LLMs) are trained on extensive datasets that encapsulate substantial world knowledge. However, their outputs often include confidently stated inaccuracies. Earlier works suggest that LLMs encode truthfulness as a dis…

TK-Mamba: Marrying KAN With Mamba for Text-Driven 3D Medical Image Segmentation Open

Haoyu Yang, Yuxiang Cai, Jintao Chen, Xuhong Zhang, Wenhui Lei , et al. · 2025

3D medical image segmentation is important for clinical diagnosis and treatment but faces challenges from high-dimensional data and complex spatial dependencies. Traditional single-modality networks, such as CNNs and Transformers, are ofte…

LightRouter: Towards Efficient LLM Collaboration with Minimal Overhead Open

Xinkui Zhao, Zuxin Wang, Guanjie Cheng, Shuiguang Deng, Jianwei Yin · 2025

The rapid advancement of large language models has unlocked remarkable capabilities across a diverse array of natural language processing tasks. However, the considerable differences among available LLMs-in terms of cost, performance, and …

SortingHat: Redefining Operating Systems Education with a Tailored Digital Teaching Assistant Open

Y L Zhang, Xinkui Zhao, Zuxin Wang, Zhengnan Zhou, Guanjie Cheng , et al. · 2025

Scalable Multi-Stage Influence Function for Large Language Models via Eigenvalue-Corrected Kronecker-Factored Parameterization Open

Yinghui Bao, Xuhong Zhang, Tianyu Du, Xinkui Zhao, Jiang Zong , et al. · 2025

Pre-trained large language models (LLMs) are commonly fine-tuned to adapt to downstream tasks. Since the majority of knowledge is acquired during pre-training, attributing the predictions of fine-tuned LLMs to their pre-training data may p…

Exploring Chinese Consumers’ Perception and Potential Acceptance of Cell-Cultured Meat and Plant-Based Meat: A Focus Group Study and Content Analysis Open

Muhabaiti Pareti, Jie Guo, Jianwei Yin, Qiankun Liu, Nadire Abudurofu , et al. · 2025

(1) Background: In recent years, meat alternatives, including plant-based and animal cell-cultured meat, have attracted substantial interest among Chinese food science researchers and consumers, prompting considerable debate; (2) Methods: …

Mer <i>K</i> ury: Adaptive Resource Allocation to Enhance the <i>K</i> ubernetes Performance for Large-Scale Clusters Open

Jiayin Luo, Xinkui Zhao, Yuxin Ma, Shengye Pang, Jianwei Yin · 2025

Jianwei Yin YOU? Author Swipe