210 citations
- Beijing University of Posts and TelecommunicationsCN7 papers
- Nanyang Technological UniversitySG2 papers
- Purple Mountain LaboratoriesCN2 papers
- Shanghai Jiao Tong UniversityCN2 papers
- Singapore University of Technology and DesignSG2 papers
- Southeast UniversityCN2 papers
- Tsinghua UniversityCN2 papers
- University of MacauMO2 papers
- American University of SharjahAE1 paper
- Beihang UniversityCN1 paper
- Beijing Jiaotong UniversityCN1 paper
- Central China Normal UniversityCN1 paper
30 papers
Proper Sea Surface Roughness Enhances the Performance of Near-Shore Maritime Networks
Wen-Yu Dong, Shaoshi Yang, Song Zhao +5
Accurate performance analysis for near-shore maritime wireless communication is essential for ensuring robust and reliable operations. However, existing analytical models often rel…
AgentChaos: Chaos Engineering for Agent Systems via Programmatic Fault Injection
Gou Tan, Zhensu Sun, Jieke Shi +10
Agent systems rely on LLM APIs for every response, but these APIs can return server errors, truncated responses, or corrupted content that propagates through downstream agents and…
KAConvNet: Kolmogorov-Arnold Convolutional Networks for Vision Recognition
Zhaoxiang Liu, Zhicheng Ma, Kaikai Zhao +2
The Convolutional Neural Networks (CNNs) have been the dominant and effective approach for general computer vision tasks. Recently, Kolmogorov-Arnold neural networks (KANs), based…
Learning Project-wise Subsequent Code Edits via Interleaving Neural-based Induction and Tool-based Deduction
Chenyan Liu, Yun Lin, Yuhuan Huang +5
In industrial and open-source software engineering tasks, developers often perform project-wise code editing tasks, including feature enhancement, refactoring, and bug fixing, wher…
An Integrated Fusion Framework for Ensemble Learning Leveraging Gradient Boosting and Fuzzy Rule-Based Models
Jinbo Li, Peng Liu, Long Chen +2
The integration of different learning paradigms has long been a focus of machine learning research, aimed at overcoming the inherent limitations of individual methods. Fuzzy rule-b…
An Efficient, Reliable and Observable Collective Communication Library in Large-scale GPU Training Clusters
Mingjun Zhang, Xiaohe Hu, Menghao Zhang +21
Large-scale LLM training requires collective communication libraries to exchange data among distributed GPUs. As a company dedicated to building and operating large-scale GPU train…