Zobrazeno 1 - 10
of 34 390
pro vyhledávání: '"An, Junyi"'
Autor:
Zhu, Yifan, Liu, Runze, Yi, Ailun, Wang, Xudong, Qin, Yuanhao, Zhao, Zihao, Zhao, Junyi, Chen, Bowen, Zhang, Xiuqi, Song, Sannian, Huo, Yongheng, Ou, Xin, Zhang, Jiaxiang
The ability to control nonclassical light emission from a single quantum emitter by an integrated cavity may unleash new perspectives for integrated photonic quantum applications. However, coupling a single quantum emitter to cavity within photonic c
Externí odkaz:
http://arxiv.org/abs/2411.06677
In text recognition, complex glyphs and tail classes have always been factors affecting model performance. Specifically for Chinese text recognition, the lack of shape-awareness can lead to confusion among close complex characters. Since such charact
Externí odkaz:
http://arxiv.org/abs/2411.06381
Autor:
Li, Junyi, Huang, Heng
Bilevel Optimization has experienced significant advancements recently with the introduction of new efficient algorithms. Mirroring the success in single-level optimization, stochastic gradient-based algorithms are widely used in bilevel optimization
Externí odkaz:
http://arxiv.org/abs/2411.05868
Controller Area Networks (CANs) are widely adopted in real-time automotive control and are increasingly standard in factory automation. Considering their critical application in safety-critical systems, The error rate of the system must be accurately
Externí odkaz:
http://arxiv.org/abs/2411.05835
Autor:
Wang, Jin, Guo, Bocheng, Li, Yijie, Wang, Junyi, Chen, Yuqian, Rushmore, Jarrett, Makris, Nikos, Rathi, Yogesh, O'Donnell, Lauren J, Zhang, Fan
Tractography fiber clustering using diffusion MRI (dMRI) is a crucial strategy for white matter (WM) parcellation. Current methods primarily use the geometric information of fibers (i.e., the spatial trajectories) to group similar fibers into cluster
Externí odkaz:
http://arxiv.org/abs/2411.01859
Autor:
Liu, Weiqi, Ai, Xi, Zhou, Zhijian, Qu, Chao, An, Junyi, Zhou, Zhipeng, Cheng, Yuan, Xu, Yinghui, Cao, Fenglei, Qi, Alan
Artificial intelligence is revolutionizing computational chemistry, bringing unprecedented innovation and efficiency to the field. To further advance research and expedite progress, we introduce the Quantum Open Organic Molecular (QO2Mol) database --
Externí odkaz:
http://arxiv.org/abs/2410.19316
Spatial intelligence is the ability of a machine to perceive, reason, and act in three dimensions within space and time. Recent advancements in large-scale auto-regressive models have demonstrated remarkable capabilities across various reasoning task
Externí odkaz:
http://arxiv.org/abs/2410.18962
Consider the math problem: "Lily received 3 cookies from her best friend yesterday and ate 5 for breakfast. Today, her friend gave her 3 more cookies. How many cookies does Lily have now?" Many large language models (LLMs) in previous research approa
Externí odkaz:
http://arxiv.org/abs/2410.18921
The mathematical capabilities of AI systems are complex and multifaceted. Most existing research has predominantly focused on the correctness of AI-generated solutions to mathematical problems. In this work, we argue that beyond producing correct ans
Externí odkaz:
http://arxiv.org/abs/2410.18336
Publikováno v:
38th Conference on Neural Information Processing Systems (NeurIPS 2024)
Federated Learning (FL) is an evolving paradigm that enables multiple parties to collaboratively train models without sharing raw data. Among its variants, Vertical Federated Learning (VFL) is particularly relevant in real-world, cross-organizational
Externí odkaz:
http://arxiv.org/abs/2410.17986