Zobrazeno 1 - 10
of 65
pro vyhledávání: '"Niu, Chaoyue"'
Existing work on large language model (LLM) personalization assigned different responding roles to LLM, but overlooked the diversity of questioners. In this work, we propose a new form of questioner-aware LLM personalization, generating different res
Externí odkaz:
http://arxiv.org/abs/2412.11736
Large text-to-image models demonstrate impressive generation capabilities; however, their substantial size necessitates expensive cloud servers for deployment. Conversely, light-weight models can be deployed on edge devices at lower cost but often wi
Externí odkaz:
http://arxiv.org/abs/2411.13787
Many large vision models have been deployed on the cloud for real-time services. Meanwhile, fresh samples are continuously generated on the served mobile device. How to leverage the device-side samples to improve the cloud-side large model becomes a
Externí odkaz:
http://arxiv.org/abs/2303.10361
One-Time Model Adaptation to Heterogeneous Clients: An Intra-Client and Inter-Image Attention Design
The mainstream workflow of image recognition applications is first training one global model on the cloud for a wide range of classes and then serving numerous clients, each with heterogeneous images from a small subset of classes to be recognized. F
Externí odkaz:
http://arxiv.org/abs/2211.06276
To meet the practical requirements of low latency, low cost, and good privacy in online intelligent services, more and more deep learning models are offloaded from the cloud to mobile devices. To further deal with cross-device data heterogeneity, the
Externí odkaz:
http://arxiv.org/abs/2211.01163
Autor:
Lv, Chengfei, Niu, Chaoyue, Gu, Renjie, Jiang, Xiaotang, Wang, Zhaode, Liu, Bin, Wu, Ziqi, Yao, Qiulin, Huang, Congyu, Huang, Panos, Huang, Tao, Shu, Hui, Song, Jinde, Zou, Bin, Lan, Peng, Xu, Guohuan, Wu, Fei, Tang, Shaojie, Wu, Fan, Chen, Guihai
To break the bottlenecks of mainstream cloud-based machine learning (ML) paradigm, we adopt device-cloud collaborative ML and build the first end-to-end and general-purpose system, called Walle, as the foundation. Walle consists of a deployment platf
Externí odkaz:
http://arxiv.org/abs/2205.14833
Autor:
Gu, Renjie, Niu, Chaoyue, Yan, Yikai, Wu, Fan, Tang, Shaojie, Jia, Rongfeng, Lyu, Chengfei, Chen, Guihai
Data heterogeneity is an intrinsic property of recommender systems, making models trained over the global data on the cloud, which is the mainstream in industry, non-optimal to each individual user's local data distribution. To deal with data heterog
Externí odkaz:
http://arxiv.org/abs/2201.10382
Autor:
Ding, Yucheng, Niu, Chaoyue, Wu, Fan, Tang, Shaojie, Lv, Chengfei, Feng, Yanghe, Chen, Guihai
We study practical data characteristics underlying federated learning, where non-i.i.d. data from clients have sparse features, and a certain client's local data normally involves only a small part of the full model, called a submodel. Due to data sp
Externí odkaz:
http://arxiv.org/abs/2109.07704
Federated learning allows mobile clients to jointly train a global model without sending their private data to a central server. Extensive works have studied the performance guarantee of the global model, however, it is still unclear how each individ
Externí odkaz:
http://arxiv.org/abs/2012.10936
Robot swarms to date are not prepared for autonomous navigation such as path planning and obstacle detection in forest floor, unable to achieve low-cost. The development of depth sensing and embedded computing hardware paves the way for swarm of terr
Externí odkaz:
http://arxiv.org/abs/2012.02907