2 papers
cs.CV2025
VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference
Shengling Qin, Hao Yu, Chenxin Wu +10
This paper presents VLCache, a cache reuse framework that exploits both Key-Value (KV) cache and encoder cache from prior multimodal inputs to eliminate costly recomputation when t…
cs.DC2025
Optimal Expert Selection for Distributed Mixture-of-Experts at the Wireless Edge
Shengling Qin, Hai Wu, Hongyang Du +1
The emergence of distributed Mixture-of-Experts (DMoE) systems, which deploy expert models at edge nodes, offers a pathway to achieving connected intelligence in sixth-generation (…