DeDelayed: Deleting Remote Inference Delay via On-Device Correction

ArXi:2510.13714v3 Announce Type: replace-cross Video comprises the vast majority of bits that are generated daily, and is the primary signal driving current innovations in robotics, remote sensing, and wearable technology. Yet, the most powerful video understanding models are too expensive for the resource-constrained platforms used in these applications. One approach is to offload inference to the cloud; this gives access to GPUs capable of processing high-resolution videos in real time.