5 papers
LeanStream: A Speculate-and-Refine Streaming Framework for Efficient on-Device LLM Inference
Renyuan Liu, Yuyang Leng, Kaiyan Liu +7
On-device LLM inference is attractive for privacy and responsiveness, but remains challenging on mobile and embedded devices because model weights far exceed available DRAM. Prior…
Physical Self-Supervised Learning: IMU Sensing without Manual Labels
Yuyang Leng, Renyuan Liu, Shaohan Hu +4
Deep neural networks have become a promising approach for IMU-based sensing, but their scalability is fundamentally limited by costly labeled data and poor robustness to heterogene…
Error Bound Analysis of Physics-Informed Neural Networks-Driven T2 Quantification in Cardiac Magnetic Resonance Imaging
Mengxue Zhang, Qingrui Cai, Yinyin Chen +13
Physics-Informed Neural Networks (PINN) are emerging as a promising approach for quantitative parameter estimation of Magnetic Resonance Imaging (MRI). While existing deep learning…
DAF: An Efficient End-to-End Dynamic Activation Framework for on-Device DNN Training
Renyuan Liu, Yuyang Leng, Kaiyan Liu +6
Recent advancements in on-device training for deep neural networks have underscored the critical need for efficient activation compression to overcome the memory constraints of mob…
Simultaneous Deep Learning of Myocardium Segmentation and T2 Quantification for Acute Myocardial Infarction MRI
Yirong Zhou, Chengyan Wang, Mengtian Lu +17
In cardiac Magnetic Resonance Imaging (MRI) analysis, simultaneous myocardial segmentation and T2 quantification are crucial for assessing myocardial pathologies. Existing methods…