Zobrazeno 1 - 10
of 647
pro vyhledávání: '"An, Ruichuan"'
Autor:
An, Ruichuan, Yang, Sihan, Lu, Ming, Zeng, Kai, Luo, Yulin, Chen, Ying, Cao, Jiajun, Liang, Hao, She, Qi, Zhang, Shanghang, Zhang, Wentao
Current vision-language models (VLMs) show exceptional abilities across diverse tasks including visual question answering. To enhance user experience in practical applications, recent studies investigate VLM personalization to understand user-provide
Externí odkaz:
http://arxiv.org/abs/2411.11706
Autor:
Li, Zheng, Wu, Siyuan, Chen, Ruichuan, Aditya, Paarijaat, Akkus, Istemi Ekin, Vanga, Manohar, Zhang, Min, Li, Hao, Zhang, Yang
Machine learning (ML), driven by prominent paradigms such as centralized and federated learning, has made significant progress in various critical applications ranging from autonomous driving to face recognition. However, its remarkable success has b
Externí odkaz:
http://arxiv.org/abs/2408.02131
Graph neural networks (GNNs) have demonstrated remarkable success in numerous graph analytical tasks. Yet, their effectiveness is often compromised in real-world scenarios due to distribution shifts, limiting their capacity for knowledge transfer acr
Externí odkaz:
http://arxiv.org/abs/2407.19311
The distribution of subpopulations is an important property hidden within a dataset. Uncovering and analyzing the subpopulation distribution within datasets provides a comprehensive understanding of the datasets, standing as a powerful tool beneficia
Externí odkaz:
http://arxiv.org/abs/2405.02363
Autor:
Lin, Weifeng, Wei, Xinyu, An, Ruichuan, Gao, Peng, Zou, Bocheng, Luo, Yulin, Huang, Siyuan, Zhang, Shanghang, Li, Hongsheng
The interaction between humans and artificial intelligence (AI) is a crucial factor that reflects the effectiveness of multimodal large language models (MLLMs). However, current MLLMs primarily focus on image-level comprehension and limit interaction
Externí odkaz:
http://arxiv.org/abs/2403.20271
In Federated Learning (FL), common privacy-enhancing techniques, such as secure aggregation and distributed differential privacy, rely on the critical assumption of an honest majority among participants to withstand various attacks. In practice, howe
Externí odkaz:
http://arxiv.org/abs/2401.02880
With the rapid growth in the scale of pre-trained foundation models, parameter-efficient fine-tuning techniques have gained significant attention, among which Adapter Tuning is the most widely used. Despite achieving efficiency, it still underperform
Externí odkaz:
http://arxiv.org/abs/2312.02923
Autor:
Zhao, Jianchen, Tseng, Cheng-Ching, Lu, Ming, An, Ruichuan, Wei, Xiaobao, Sun, He, Zhang, Shanghang
Emerging Implicit Neural Representation (INR) is a promising data compression technique, which represents the data using the parameters of a Deep Neural Network (DNN). Existing methods manually partition a complex scene into local regions and overfit
Externí odkaz:
http://arxiv.org/abs/2312.01361
Autor:
Ruichuan Li, Qingguang Zhang, Zhengyu Li, Wentao Yuan, Qiyou Sun, Junru Yang, Yuhang Sun, Lanzheng Chen, Dongrun Li, Shipeng Shangguan
Publikováno v:
Alexandria Engineering Journal, Vol 114, Iss , Pp 556-571 (2025)
High-pressure common rail fuel injection technology diesel engine control technology core, and common rail injector are the soul of the technology. During cold start or high-speed operation of a diesel engine, the combustion chamber is prone to uneve
Externí odkaz:
https://doaj.org/article/492e8ec1d19249e8944f2c1a894adf28
Autor:
Yu, Minchen, Wang, Ao, Chen, Dong, Yu, Haoxuan, Luo, Xiaonan, Li, Zhuohao, Wang, Wei, Chen, Ruichuan, Nie, Dapeng, Yang, Haoran
Serverless computing has become increasingly popular for machine learning inference. However, current serverless platforms lack efficient support for GPUs, limiting their ability to deliver low-latency inference. In this paper, we propose FaaSwap, a
Externí odkaz:
http://arxiv.org/abs/2306.03622