51 citations · 165 across the 41 of their papers we have counts for
7 papers · 1 filter
Generative AI Meets 6G and Beyond: Diffusion Models for Semantic Communications
Hai-Long Qin, Jincheng Dai, Guo Lu +6
Semantic communications mark a paradigm shift from bit-accurate transmission toward meaning-centric communication, essential as wireless systems approach theoretical capacity limit…
NeRFCom: Feature Transform Coding Meets Neural Radiance Field for Free-View 3D Scene Semantic Transmission
Weijie Yue, Zhongwei Si, Bolin Wu +5
We introduce NeRFCom, a novel communication system designed for end-to-end 3D scene transmission. Compared to traditional systems relying on handcrafted NeRF semantic feature decom…
DiffCom: Channel Received Signal is a Natural Condition to Guide Diffusion Posterior Sampling
Sixian Wang, Jincheng Dai, Kailin Tan +3
End-to-end visual communication systems typically optimize a trade-off between channel bandwidth costs and signal-level distortion metrics. However, under challenging physical cond…
SwinJSCC: Taming Swin Transformer for Deep Joint Source-Channel Coding
Ke Yang, Sixian Wang, Jincheng Dai +3
As one of the key techniques to realize semantic communications, end-to-end optimized neural joint source-channel coding (JSCC) has made great progress over the past few years. A g…
Toward Intelligent and Efficient 6G Networks: JCSC Enabled On-Purpose Machine Communications
Ping Zhang, Heng Yang, Zhiyong Feng +5
Driven by the vision of "intelligent connection of everything" toward 6G, the collective intelligence of networked machines can be fully exploited to improve system efficiency by s…
NeurJSCC Enabled Semantic Communications: Paradigms, Applications, and Potentials
Sixian Wang, Jincheng Dai, Xiaoqi Qin +2
Recent advances in deep learning have led to increased interest in solving high-efficiency end-to-end transmission problems using methods that employ the nonlinear property of neur…
Improved Nonlinear Transform Source-Channel Coding to Catalyze Semantic Communications
Sixian Wang, Jincheng Dai, Xiaoqi Qin +3
Recent deep learning methods have led to increased interest in solving high-efficiency end-to-end transmission problems. These methods, we call nonlinear transform source-channel c…