306 citations
- The University of SydneyAU10 papers
- University of Science and Technology of ChinaCN8 papers
- Tsinghua UniversityCN7 papers
- Chinese Academy of SciencesCN6 papers
- JDSU (United States)US6 papers
- University of Chinese Academy of SciencesCN6 papers
- Beihang UniversityCN4 papers
- Wuhan UniversityCN4 papers
- Association for Computing MachineryUS3 papers
- Baidu (China)CN3 papers
- City University of Hong KongHK3 papers
- Institute of Computing TechnologyCN3 papers
11 papers · 1 filter
Federated Continual Learning via Knowledge Fusion: A Survey
Xin Yang, Hao Yu, Xin Gao +3
Data privacy and silos are nontrivial and greatly challenging in many real-world applications. Federated learning is a decentralized approach to training models across multiple loc…
Rethinking Large-scale Pre-ranking System: Entire-chain Cross-domain Models
Jinbo Song, Ruoran Huang, Xinyang Wang +9
Industrial systems such as recommender systems and online advertising, have been widely equipped with multi-stage architectures, which are divided into several cascaded modules, in…
Bidirectional Knowledge Reconfiguration for Lightweight Point Cloud Analysis
Peipei Li, Xing Cui, Yibo Hu +3
Point cloud analysis faces computational system overhead, limiting its application on mobile or edge devices. Directly employing small models may result in a significant drop in pe…
Differentiable Retrieval Augmentation via Generative Language Modeling for E-commerce Query Intent Classification
Chenyu Zhao, Yunjiang Jiang, Yiming Qiu +2
Retrieval augmentation, which enhances downstream models by a knowledge retriever and an external corpus instead of by merely increasing the number of model parameters, has been su…
Learning and Evaluating Human Preferences for Conversational Head Generation
Mohan Zhou, Yalong Bai, Wei Zhang +3
A reliable and comprehensive evaluation metric that aligns with manual preference assessments is crucial for conversational head video synthesis methods development. Existing quant…
LGViT: Dynamic Early Exiting for Accelerating Vision Transformer
Guanyu Xu, Jiawei Hao, Li Shen +4
Recently, the efficient deployment and acceleration of powerful vision transformers (ViTs) on resource-limited edge devices for providing multimedia services have become attractive…