Search

Your search keyword '"Shen, Xinyi"' showing total 646 results
Start Over Author "Shen, Xinyi"
646 results on '"Shen, Xinyi"'

3. Local and Global Contexts for Conversation

Author

Lin, Zuoquan and Shen, Xinyi

Subjects
Computer Science - Computation and Language
Abstract

The context in conversation is the dialog history crucial for multi-turn dialogue. Learning from the relevant contexts in dialog history for grounded conversation is a challenging problem. Local context is the most neighbor and more sensitive to the subsequent response, and global context is relevant to a whole conversation far beyond neighboring utterances. Currently, pretrained transformer models for conversation challenge capturing the correlation and connection between local and global contexts. We introduce a local and global conversation model (LGCM) for general-purpose conversation in open domain. It is a local-global hierarchical transformer model that excels at accurately discerning and assimilating the relevant contexts necessary for generating responses. It employs a local encoder to grasp the local context at the level of individual utterances and a global encoder to understand the broader context at the dialogue level. The seamless fusion of these locally and globally contextualized encodings ensures a comprehensive comprehension of the conversation. Experiments on popular datasets show that LGCM outperforms the existing conversation models on the performance of automatic metrics with significant margins., Comment: 11 pages, 3 figures

Published
2024

6. Context-dependent roles for ubiquitous mitochondrial creatine kinase CKMT1 in breast cancer progression

Author

Ayyappan, Vinay, primary, Jenkinson, Nicole M., additional, Tressler, Caitlin M., additional, Tan, Zheqiong, additional, Cheng, Menglin, additional, Shen, Xinyi Elaine, additional, Guerrero, Alejandro, additional, Sonkar, Kanchan, additional, Cai, Ruoqing, additional, Adelaja, Oluwatobi, additional, Roy, Sujayita, additional, Meeker, Alan, additional, Argani, Pedram, additional, and Glunde, Kristine, additional

Published
2024
Full Text
View/download PDF

9. Dynamic Clinical Success Rates for Drugs in the 21st Century

Author

Zhu, Feng, primary, Zhou, Ying, additional, Zhang, Yintao, additional, Chen, Zhen, additional, Huang, Shijie, additional, Li, Yinghong, additional, Fu, Jianbo, additional, Zhang, Hongning, additional, Zhao, Donghai, additional, Lian, Xichen, additional, Zhou, Yuan, additional, Shen, Xinyi, additional, Qiu, Yunqing, additional, and Han, Lianyi, additional

Published
2024
Full Text
View/download PDF

14. UADB: Unsupervised Anomaly Detection Booster

Author

Ye, Hangting, Liu, Zhining, Shen, Xinyi, Cao, Wei, Zheng, Shun, Gui, Xiaofan, Zhang, Huishuai, Chang, Yi, and Bian, Jiang

Subjects
Computer Science - Machine Learning
Abstract

Unsupervised Anomaly Detection (UAD) is a key data mining problem owing to its wide real-world applications. Due to the complete absence of supervision signals, UAD methods rely on implicit assumptions about anomalous patterns (e.g., scattered/sparsely/densely clustered) to detect anomalies. However, real-world data are complex and vary significantly across different domains. No single assumption can describe such complexity and be valid in all scenarios. This is also confirmed by recent research that shows no UAD method is omnipotent. Based on above observations, instead of searching for a magic universal winner assumption, we seek to design a general UAD Booster (UADB) that empowers any UAD models with adaptability to different data. This is a challenging task given the heterogeneous model structures and assumptions adopted by existing UAD methods. To achieve this, we dive deep into the UAD problem and find that compared to normal data, anomalies (i) lack clear structure/pattern in feature space, thus (ii) harder to learn by model without a suitable assumption, and finally, leads to (iii) high variance between different learners. In light of these findings, we propose to (i) distill the knowledge of the source UAD model to an imitation learner (booster) that holds no data assumption, then (ii) exploit the variance between them to perform automatic correction, and thus (iii) improve the booster over the original UAD model. We use a neural network as the booster for its strong expressive power as a universal approximator and ability to perform flexible post-hoc tuning. Note that UADB is a model-agnostic framework that can enhance heterogeneous UAD models in a unified way. Extensive experiments on over 80 tabular datasets demonstrate the effectiveness of UADB., Comment: IEEE 39th International Conference on Data Engineering (ICDE 2023)

Published
2023

16. An Empirical Study on Context Length for Open-Domain Dialog Generation

Author

Shen, Xinyi, Lin, Zuoquan, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Liu, Fenrong, editor, Sadanandan, Arun Anand, editor, Pham, Duc Nghia, editor, Mursanto, Petrus, editor, and Lukose, Dickson, editor

Published
2024
Full Text
View/download PDF

17. Dynamic Clinical Success Rates for Drugs in the 21st Century

Author

Zhou, Ying, primary, Zhang, Yintao, additional, Chen, Zhen, additional, Huang, Shijie, additional, Li, Yinghong, additional, Fu, Jianbo, additional, Zhang, Hongning, additional, Zhao, Donghai, additional, Lian, Xichen, additional, Zhou, Yuan, additional, Shen, Xinyi, additional, Qiu, Yunqing, additional, Han, Lianyi, additional, and Zhu, Feng, additional

Published
2024
Full Text
View/download PDF

30. FluoMALDI Microscopy: Matrix Co‐Crystallization Simultaneously Enhances Fluorescence and MALDI Imaging

Author

Yang, Ethan, primary, Shen, Xinyi Elaine, additional, West‐Foyle, Hoku, additional, Hahm, Tae‐Hun, additional, Siegler, Maxime A., additional, Brown, Dalton R., additional, Johnson, Cole C., additional, Kim, Jeong Hee, additional, Roker, LaToya Ann, additional, Tressler, Caitlin M., additional, Barman, Ishan, additional, Kuo, Scot C., additional, and Glunde, Kristine, additional

Published
2023
Full Text
View/download PDF

31. TheMarker: a comprehensive database of therapeutic biomarkers

Author

Zhang, Yintao, primary, Zhou, Ying, additional, Zhou, Yuan, additional, Yu, Xinyuan, additional, Shen, Xinyi, additional, Hong, Yanfeng, additional, Zhang, Yuxin, additional, Wang, Shanshan, additional, Mou, Minjie, additional, Zhang, Jinsong, additional, Tao, Lin, additional, Gao, Jianqing, additional, Qiu, Yunqing, additional, Chen, Yuzong, additional, and Zhu, Feng, additional

Published
2023
Full Text
View/download PDF

40. Interfacial Polymerization Produced Magnetic Particles with Nano‐Filopodia for Highly Accurate Liquid Biopsy in The Psa Gray Zone

Author

Zhang, Yue, primary, Zhang, Fan, additional, Song, Yongyang, additional, Shen, Xinyi, additional, Bu, Fanqin, additional, Su, Dandan, additional, Luo, Chen, additional, Ge, Liyuan, additional, Deng, Shaohui, additional, Wu, Zonglong, additional, Zhang, Zhanyi, additional, Duan, Peichen, additional, Li, Nan, additional, Min, Li, additional, Zhang, Shudong, additional, and Wang, Shutao, additional

Published
2023
Full Text
View/download PDF

45. PatchFormer: An Efficient Point Transformer with Patch Attention

Author

Cheng, Zhang, Wan, Haocheng, Shen, Xinyi, and Wu, Zizhao

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

The point cloud learning community witnesses a modeling shift from CNNs to Transformers, where pure Transformer architectures have achieved top accuracy on the major learning benchmarks. However, existing point Transformers are computationally expensive since they need to generate a large attention map, which has quadratic complexity (both in space and time) with respect to input size. To solve this shortcoming, we introduce Patch ATtention (PAT) to adaptively learn a much smaller set of bases upon which the attention maps are computed. By a weighted summation upon these bases, PAT not only captures the global shape context but also achieves linear complexity to input size. In addition, we propose a lightweight Multi-Scale aTtention (MST) block to build attentions among features of different scales, providing the model with multi-scale features. Equipped with the PAT and MST, we construct our neural architecture called PatchFormer that integrates both modules into a joint framework for point cloud learning. Extensive experiments demonstrate that our network achieves comparable accuracy on general point cloud learning tasks with 9.2x speed-up than previous point Transformers., Comment: 10 pages

Published
2021

46. PVT: Point-Voxel Transformer for Point Cloud Learning

Author

Zhang, Cheng, Wan, Haocheng, Shen, Xinyi, and Wu, Zizhao

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Graphics
Abstract

The recently developed pure Transformer architectures have attained promising accuracy on point cloud learning benchmarks compared to convolutional neural networks. However, existing point cloud Transformers are computationally expensive since they waste a significant amount of time on structuring the irregular data. To solve this shortcoming, we present Sparse Window Attention (SWA) module to gather coarse-grained local features from non-empty voxels, which not only bypasses the expensive irregular data structuring and invalid empty voxel computation, but also obtains linear computational complexity with respect to voxel resolution. Meanwhile, to gather fine-grained features about the global shape, we introduce relative attention (RA) module, a more robust self-attention variant for rigid transformations of objects. Equipped with the SWA and RA, we construct our neural architecture called PVT that integrates both modules into a joint framework for point cloud learning. Compared with previous Transformer-based and attention-based models, our method attains top accuracy of 94.0% on classification benchmark and 10x inference speedup on average. Extensive experiments also valid the effectiveness of PVT on part and semantic segmentation benchmarks (86.6% and 69.2% mIoU, respectively)., Comment: 29 pages

Published
2021

48. Chloride‐Based Additive Engineering For Efficient and Stable Wide‐Bandgap Perovskite Solar Cells

Author

Shen, Xinyi, primary, Gallant, Benjamin M., additional, Holzhey, Philippe, additional, Smith, Joel A., additional, Elmestekawy, Karim A., additional, Yuan, Zhongcheng, additional, Rathnayake, P. V. G. M., additional, Bernardi, Stefano, additional, Dasgupta, Akash, additional, Kasparavicius, Ernestas, additional, Malinauskas, Tadas, additional, Caprioglio, Pietro, additional, Shargaieva, Oleksandra, additional, Lin, Yen‐Hung, additional, McCarthy, Melissa M., additional, Unger, Eva, additional, Getautis, Vytautas, additional, Widmer‐Cooper, Asaph, additional, Herz, Laura M., additional, and Snaith, Henry J., additional

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results