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
The proposed LaSR (Latent Speech Reasoning), a novel training paradigm featuring a context-aware reasoning trajectory that leverages the latent reasoning process, significantly improves terminology recognition without introducing additional latency and consistently outperforms standard supervised fine-tuning baselines.
S$^3$-Bench is introduced, a systematic evaluation framework covering 10 major disciplines, consisting of a Knowledge set for speech question-answering and a Dialogue set for multi-turn progressive interactions with simulated user agents that systematically characterize the common challenges and performance tradeoffs o...
He-Yang Liu, Jia-Yi Huang, Wen Xiao 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.