AI RESEARCH
CoStream: Codec-Guided Resource-Efficient System for Video Streaming Analytics
arXiv CS.LG
•
ArXi:2604.06036v1 Announce Type: cross Video streaming analytics is a crucial workload for vision-language model serving, but the high cost of multimodal inference limits scalability. Prior systems reduce inference cost by exploiting temporal and spatial redundancy in video streams, but they target either the vision transformer (ViT) or the LLM with a limited view, leaving end-to-end opportunities untapped. Moreover, existing methods incur significant overhead to identify redundancy, either through offline profiling and