Our demo “MuRa: A Scalable Mobile Ultra-wideband Testbed for Multi-node Ranging” received the Best Demo Award at MobiSys 2024! Congrats to Shaoyang!
ArtFL, a novel federated learning system designed to support dynamic runtime inference through multi-scale training. The key idea of ArtFL is to utilize the data resolution, i.e., frame resolution of videos, as a knob to accommodate dynamic inference latency requirements. Specifically, we initially propose data-utility-based multi-scale training, allowing the trained model to process data of varying resolutions during inference.
Our paper “ArtFL: Exploiting Data Resolution in Federated Learning for Dynamic Runtime Inference via Multi-Scale Training” received the Best Paper Award at IPSN…
Our demo “AD-CLIP: Privacy-Preserving, Low-Cost Synthetic Human Action Dataset for Alzheimer’s Patients via CLIP-based Models” received the Best Demo Award at IPSN 2024! Congrats…
Congratulations to Xiaomin who will be joing CSE@HKUST as a tenure-track Assistant Professor in Fall 2024!
Our research projects, VI-Map, Mozart, and VibVoice have won gold, silver, and bronze prizes at the 49th International Exhibition of Inventions Geneva, respectively.
Our paper “VI-Map: Infrastructure-Assisted Real-Time HD Mapping for Autonomous Driving” received Best Community Contribution Award at MobiCom 2023!