Zobrazeno 1 - 10
of 2 211
pro vyhledávání: '"An, Yatong"'
With the widespread adoption of 5G and Internet of Things (IoT) technologies, the low latency provided by edge computing has great importance for real-time processing. However, managing numerous simultaneous service requests poses a significant chall
Externí odkaz:
http://arxiv.org/abs/2409.09063
Major search engine providers are rapidly incorporating Large Language Model (LLM)-generated content in response to user queries. These conversational search engines operate by loading retrieved website text into the LLM context for summarization and
Externí odkaz:
http://arxiv.org/abs/2406.03589
The structured light projection technique is a representative active method for 3-D reconstruction, but many researchers face challenges with the intricate projector calibration process. To address this complexity, we employs an additional camera, te
Externí odkaz:
http://arxiv.org/abs/2403.01119
Adversarial robustness often comes at the cost of degraded accuracy, impeding real-life applications of robust classification models. Training-based solutions for better trade-offs are limited by incompatibilities with already-trained high-performanc
Externí odkaz:
http://arxiv.org/abs/2402.02263
Autor:
Bai, Yatong, Garg, Utsav, Shanker, Apaar, Zhang, Haoming, Parajuli, Samyak, Bas, Erhan, Filipovic, Isidora, Chu, Amelia N., Fomitcheva, Eugenia D, Branson, Elliot, Kim, Aerin, Sojoudi, Somayeh, Cho, Kyunghyun
Vision and vision-language applications of neural networks, such as image classification and captioning, rely on large-scale annotated datasets that require non-trivial data-collecting processes. This time-consuming endeavor hinders the emergence of
Externí odkaz:
http://arxiv.org/abs/2401.04575
Deep neural classifiers have recently found tremendous success in data-driven control systems. However, existing models suffer from a trade-off between accuracy and adversarial robustness. This limitation must be overcome in the control of safety-cri
Externí odkaz:
http://arxiv.org/abs/2311.15165
Diffusion models are instrumental in text-to-audio (TTA) generation. Unfortunately, they suffer from slow inference due to an excessive number of queries to the underlying denoising network per generation. To address this bottleneck, we introduce Con
Externí odkaz:
http://arxiv.org/abs/2309.10740
Imitation learning suffers from causal confusion. This phenomenon occurs when learned policies attend to features that do not causally influence the expert actions but are instead spuriously correlated. Causally confused agents produce low open-loop
Externí odkaz:
http://arxiv.org/abs/2307.15980
Autor:
Zhihua Li, Yatong Wu, Jicong Du, Wen Qian, Sinian Wang, Fengsheng Li, Suhe Dong, Shunchang Jiao
Publikováno v:
Molecular Medicine, Vol 30, Iss 1, Pp 1-13 (2024)
Abstract Background Ionizing radiation (IR), including radiotherapy, can exert lasting harm on living organisms. While liposaccharide (LPS) offers resistance to radiation damage, it also induces toxic responses. Thankfully, an LPS analogue called N-f
Externí odkaz:
https://doaj.org/article/58080e0a22f34c9c98517f9d3726bfed
Autor:
Jingxiao Zhang, Yatong Li, Lei Liu, Feifei Dai, Yujing Peng, Qiuying Ma, Lin Li, Yu Hong, Aihua Liu, Xinghu Zhang, Xiaohui Wang, Junying He, Hui Bu, Yanjun Guo, Hanqiu Jiang, Shilei Cui, Houliang Sun, Jiawei Wang
Publikováno v:
BMC Neurology, Vol 24, Iss 1, Pp 1-12 (2024)
Abstract Background Recognizing the predictors of poor short-term prognosis after first-line immunotherapy in patients with anti-N-methyl-D-aspartate receptor (anti-NMDAR) encephalitis is essential for individualized treatment strategy. The objective
Externí odkaz:
https://doaj.org/article/d6440f0513974a92962e6fbdda44c9b0