Search

Your search keyword '"Wu, Lingling"' showing total 1,707 results
Start Over Author "Wu, Lingling"
1,707 results on '"Wu, Lingling"'

2. MOSS: An Open Conversational Large Language Model

Author

Sun, Tianxiang, Zhang, Xiaotian, He, Zhengfu, Li, Peng, Cheng, Qinyuan, Liu, Xiangyang, Yan, Hang, Shao, Yunfan, Tang, Qiong, Zhang, Shiduo, Zhao, Xingjian, Chen, Ke, Zheng, Yining, Zhou, Zhejian, Li, Ruixiao, Zhan, Jun, Zhou, Yunhua, Li, Linyang, Yang, Xiaogui, Wu, Lingling, Yin, Zhangyue, Huang, Xuanjing, Jiang, Yu-Gang, and Qiu, Xipeng

Published
2024
Full Text
View/download PDF

6. FedGSM: Efficient Federated Learning for LEO Constellations with Gradient Staleness Mitigation

Author

Wu, Lingling and Zhang, Jingjing

Subjects
Electrical Engineering and Systems Science - Signal Processing
Abstract

Recent advancements in space technology have equipped low Earth Orbit (LEO) satellites with the capability to perform complex functions and run AI applications. Federated Learning (FL) on LEO satellites enables collaborative training of a global ML model without the need for sharing large datasets. However, intermittent connectivity between satellites and ground stations can lead to stale gradients and unstable learning, thereby limiting learning performance. In this paper, we propose FedGSM, a novel asynchronous FL algorithm that introduces a compensation mechanism to mitigate gradient staleness. FedGSM leverages the deterministic and time-varying topology of the orbits to offset the negative effects of staleness. Our simulation results demonstrate that FedGSM outperforms state-of-the-art algorithms for both IID and non-IID datasets, underscoring its effectiveness and advantages. We also investigate the effect of system parameters., Comment: 5 pages,6 figures

Published
2023
Full Text
View/download PDF

10. A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation

Author

Sun, Tianxiang, Liu, Xiangyang, Zhu, Wei, Geng, Zhichao, Wu, Lingling, He, Yilong, Ni, Yuan, Xie, Guotong, Huang, Xuanjing, and Qiu, Xipeng

Subjects
Computer Science - Computation and Language
Abstract

Early exiting allows instances to exit at different layers according to the estimation of difficulty. Previous works usually adopt heuristic metrics such as the entropy of internal outputs to measure instance difficulty, which suffers from generalization and threshold-tuning. In contrast, learning to exit, or learning to predict instance difficulty is a more appealing way. Though some effort has been devoted to employing such "learn-to-exit" modules, it is still unknown whether and how well the instance difficulty can be learned. As a response, we first conduct experiments on the learnability of instance difficulty, which demonstrates that modern neural models perform poorly on predicting instance difficulty. Based on this observation, we propose a simple-yet-effective Hash-based Early Exiting approach (HashEE) that replaces the learn-to-exit modules with hash functions to assign each token to a fixed exiting layer. Different from previous methods, HashEE requires no internal classifiers nor extra parameters, and therefore is more efficient. Experimental results on classification, regression, and generation tasks demonstrate that HashEE can achieve higher performance with fewer FLOPs and inference time compared with previous state-of-the-art early exiting methods., Comment: Accepted to Findings of ACL 2022

Published
2022

23. Towards Efficient NLP: A Standard Evaluation and A Strong Baseline

Author

Liu, Xiangyang, Sun, Tianxiang, He, Junliang, Wu, Jiawen, Wu, Lingling, Zhang, Xinyu, Jiang, Hao, Cao, Zhao, Huang, Xuanjing, and Qiu, Xipeng

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

Supersized pre-trained language models have pushed the accuracy of various natural language processing (NLP) tasks to a new state-of-the-art (SOTA). Rather than pursuing the reachless SOTA accuracy, more and more researchers start paying attention on model efficiency and usability. Different from accuracy, the metric for efficiency varies across different studies, making them hard to be fairly compared. To that end, this work presents ELUE (Efficient Language Understanding Evaluation), a standard evaluation, and a public leaderboard for efficient NLP models. ELUE is dedicated to depict the Pareto Frontier for various language understanding tasks, such that it can tell whether and how much a method achieves Pareto improvement. Along with the benchmark, we also release a strong baseline, ElasticBERT, which allows BERT to exit at any layer in both static and dynamic ways. We demonstrate the ElasticBERT, despite its simplicity, outperforms or performs on par with SOTA compressed and early exiting models. With ElasticBERT, the proposed ELUE has a strong Pareto Frontier and makes a better evaluation for efficient NLP models., Comment: Accepted to the main conference of NAACL-2022

Published
2021

37. Analysis of the characteristics of Salmonella senftenberg causing a food poisoning incident in 2021 in Xinxiang

Author

SHI Xiaojuan, ZHOU Yuxin, CHEN Yulian, LUAN Xubo, LIU Junke, WEI Hongxia, and WU Lingling

Subjects
food poisoning, salmonella senftenberg, serum type, drug resistance test, pulsed field gel electrophoresis, virulence gene, Food processing and manufacture, TP368-456, Nutrition. Foods and food supply, TX341-641
Abstract

ObjectiveTo analyze the pathogenic characteristics of Salmonella senftenberg isolate causing food poisoning in Xinxiang in 2021.MethodsEpidemiological investigation of food poisoning event was performed. Pathogenic bacteria were separated and identified from 11 samples. Ten Salmonella isolates were subjected to serotyping， drug susceptibility testing， detection of characteristic gene fragments （mogA， sseL， mgtC， bcfA， araB） of 5 virulence island （SPIs） and pulsed field gel electrophoresis （PFGE） typing analysis.ResultsSerum antigenic formulas of all Salmonella isolates were 1，3，19；g，s，t Salmonella senftenberg. All Salmonella isolates were resistant to cefazolin， kanamycin， gentamicin and amikacin. Among them， two isolates from the patient feces were also resistant to ampicillin， tetracycline，doxycycline，chloramphenicol，trimethoprim/sulfamethoxazole. PFGE clustering analysis showed that there was no difference in the bands among the 10 strains （2 cases strains， 5 food strains， and 3 environmental strains）， suggesting that they were highly homologous. Five Salmonella pathogenicity island characteristic gene fragments were detected among 10 isolates.ConclusionSalmonella senftenberg caused the food poisoning event. The isolates carried 5 Salmonella pathogenicity island characteristic gene fragments and 2 isolates exhibited multi-drug resistance. Relevant departments should pay more attention to this issue.

Published
2023
Full Text
View/download PDF

43. Inhibition of miR-4763-3p expression in the brains of AD-MCI mice activates the PI3K/mTOR/Bcl2 autophagy signaling pathway to reverse neuronal loss and ameliorate cognitive decline

Author

Qi, Wenxin, primary, Dong, Naijun, additional, WU, Peiru, additional, Fu, Wenjun, additional, Liu, Qian, additional, Zhang, Xueqi, additional, Wu, Hao, additional, He, Xirui, additional, Wu, Lingling, additional, Ward, Natalie, additional, Dong, Xin, additional, Liu, Yihao, additional, Zhao, Robert Chunhua, additional, and Wang, Jiao, additional

Published
2024
Full Text
View/download PDF

48. LINC00606 promotes glioblastoma progression through sponge miR-486-3p and interaction with ATP11B

Author

Dong, Naijun, primary, Qi, Wenxin, additional, Wu, Lingling, additional, Li, Jie, additional, Zhang, Xueqi, additional, Wu, Hao, additional, Zhang, Wen, additional, Jiang, Jiawen, additional, Zhang, Shibo, additional, Fu, Wenjun, additional, Liu, Qian, additional, Qi, Guandong, additional, Wang, Lukai, additional, Lu, Yanyuan, additional, Luo, Jingyi, additional, Kong, Yanyan, additional, Liu, Yihao, additional, Zhao, Robert Chunhua, additional, and Wang, Jiao, additional

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results