A unified edge-cloud system for real-time video VLM applications that integrates six representative video VLM backends with streaming or interaction-oriented capabilities and evaluates them across backend runtime, media transport, client-observed latency, and interaction behavior.
Pu-Nan Dai, Jun Xu, Bing-Cong Lu et al.· arXiv.org· 0 citations
Distributed deployment of large vision foundation models often partitions a ViT backbone and exchanges intermediate token features between computing nodes, making efficient feature compression critical under bandwidth and computation constraints. Existing ViT feature codecs typically flatten heterogeneous global and pa...
Donghui Feng, Feng-Xi Zhang, Changsheng Gao et al.· 0 citations
The decoupled self-forcing distillation resolves both models under one frozen teacher: conditioned on motion, it distills the renderer into a block-causal student; unconditionally, it scores rendered rollouts against real videos, supervising motion by the video it produces.
Yan-Ru An, Rui-Yan Wang, Wen-Wu Wei et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.