AdaFlowLite Paper Proposes Non-blocking Inference on Asynchronous Mobile Sensor Data
A new arXiv paper, AdaFlowLite, addresses scalable, non-blocking multi-modal deep learning inference for mobile devices with sensors such as LiDAR and cameras producing asynchronous data.
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-11-18 05:00 · arXiv cs.LG
AdaFlowLite: Scalable and Non-blocking Inference on Asynchronous Mobile Data