Zobrazeno 1 - 10
of 742
pro vyhledávání: '"LI Jialong"'
Optimizing Mixture-of-Experts Inference Time Combining Model Deployment and Communication Scheduling
As machine learning models scale in size and complexity, their computational requirements become a significant barrier. Mixture-of-Experts (MoE) models alleviate this issue by selectively activating relevant experts. Despite this, MoE models are hind
Externí odkaz:
http://arxiv.org/abs/2410.17043
Optical data center networks (DCNs) are renovating the infrastructure design for the cloud in the post Moore's law era. The fact that optical DCNs rely on optical circuits of microsecond-scale durations makes nanosecond-precision time synchronization
Externí odkaz:
http://arxiv.org/abs/2410.17012
Autor:
Li, Jialong, Zhang, Zhicheng, Chen, Yunwei, Lu, Qiqi, Wu, Ye, Liu, Xiaoming, Feng, QianJin, Feng, Yanqiu, Zhang, Xinyuan
Diffusion tensor imaging (DTI) holds significant importance in clinical diagnosis and neuroscience research. However, conventional model-based fitting methods often suffer from sensitivity to noise, leading to decreased accuracy in estimating DTI par
Externí odkaz:
http://arxiv.org/abs/2409.02492
Autor:
Yang, Shiqi, Liu, Minghuan, Qin, Yuzhe, Ding, Runyu, Li, Jialong, Cheng, Xuxin, Yang, Ruihan, Yi, Sha, Wang, Xiaolong
Learning from demonstrations has shown to be an effective approach to robotic manipulation, especially with the recently collected large-scale robot data with teleoperation systems. Building an efficient teleoperation system across diverse robot plat
Externí odkaz:
http://arxiv.org/abs/2408.11805
Diffusion models, which leverage stochastic processes to capture complex data distributions effectively, have shown their performance as generative models, achieving notable success in image-related tasks through iterative denoising processes. Recent
Externí odkaz:
http://arxiv.org/abs/2408.10266
People with color vision deficiency often face challenges in distinguishing colors such as red and green, which can complicate daily tasks and require the use of assistive tools or environmental adjustments. Current support tools mainly focus on pres
Externí odkaz:
http://arxiv.org/abs/2407.04362
Rule-based adaptation is a foundational approach to self-adaptation, characterized by its human readability and rapid response. However, building high-performance and robust adaptation rules is often a challenge because it essentially involves search
Externí odkaz:
http://arxiv.org/abs/2407.02203
Teleoperation serves as a powerful method for collecting on-robot data essential for robot learning from demonstrations. The intuitiveness and ease of use of the teleoperation system are crucial for ensuring high-quality, diverse, and scalable data.
Externí odkaz:
http://arxiv.org/abs/2407.01512
This work is an improved system that we submitted to task 1 of DCASE2023 challenge. We propose a method of low-complexity acoustic scene classification by a parallel attention-convolution network which consists of four modules, including pre-processi
Externí odkaz:
http://arxiv.org/abs/2406.08119
It's assumed that training data is sufficient in base session of few-shot class-incremental audio classification. However, it's difficult to collect abundant samples for model training in base session in some practical scenarios due to the data scarc
Externí odkaz:
http://arxiv.org/abs/2406.08122