Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
MMSpec: Benchmarking Speculative Decoding for Vision-Language Models
Hui Shen, Xin Wang, Ping Zhang +11
Vision-language models (VLMs) achieve strong performance on multimodal tasks but suffer from high inference latency due to large model sizes and long multimodal contexts. Speculati…
cs.CV2024
Semantic Feature Decomposition based Semantic Communication System of Images with Large-scale Visual Generation Models
Senran Fan, Zhicheng Bao, Chen Dong +3
The end-to-end image communication system has been widely studied in the academic community. The escalating demands on image communication systems in terms of data volume, environm…
cs.CV2024
Semantic Similarity Score for Measuring Visual Similarity at Semantic Level
Senran Fan, Zhicheng Bao, Chen Dong +3
Semantic communication, as a revolutionary communication architecture, is considered a promising novel communication paradigm. Unlike traditional symbol-based error-free communicat…