1.6k citations
- Tsinghua UniversityCN23 papers
- Chinese Academy of SciencesCN20 papers
- Ministry of Industry and Information TechnologyCN20 papers
- Xidian UniversityCN19 papers
- Xi'an Jiaotong UniversityCN18 papers
- University of Chinese Academy of SciencesCN14 papers
- Australian National UniversityAU12 papers
- Nanyang Technological UniversitySG12 papers
- Fudan UniversityCN11 papers
- Moscow Institute of Physics and TechnologyRU11 papers
- Beijing Normal UniversityCN10 papers
- Centre National de la Recherche ScientifiqueFR10 papers
7 papers · 2 filters
Diffusion Models as Network Optimizers: Explorations and Analysis
Ruihuai Liang, Bo Yang, Pengyu Chen +8
Network optimization is a fundamental challenge in the Internet of Things (IoT) network, often characterized by complex features that make it difficult to solve these problems. Rec…
FastSTI: A Fast Conditional Pseudo Numerical Diffusion Model for Spatio-temporal Traffic Data Imputation
Shaokang Cheng, Nada Osman, Shiru Qu +1
High-quality spatiotemporal traffic data is crucial for intelligent transportation systems (ITS) and their data-driven applications. Inevitably, the issue of missing data caused by…
AdaShadow: Responsive Test-time Model Adaptation in Non-stationary Mobile Environments
Cheng Fang, Sicong Liu, Zimu Zhou +4
On-device adapting to continual, unpredictable domain shifts is essential for mobile applications like autonomous driving and augmented reality to deliver seamless user experiences…
Sampling and active learning methods for network reliability estimation using K-terminal spanning tree
Chen Ding, Pengfei Wei, Yan Shi +3
Network reliability analysis remains a challenge due to the increasing size and complexity of networks. This paper presents a novel sampling method and an active learning method fo…
CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community
Yan Liu, Bin Guo, Nuo Li +3
Artificial Intelligence of Things (AIoT) is an emerging frontier based on the deep fusion of Internet of Things (IoT) and Artificial Intelligence (AI) technologies. Although advanc…
Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning
Chenjia Bai, Lingxiao Wang, Jianye Hao +4
Offline Reinforcement Learning (RL) has shown promising results in learning a task-specific policy from a fixed dataset. However, successful offline RL often relies heavily on the…