Showing 2026Show all
3 papers · 1 filter
eess.IV2026
Gen2-VC: Unlocking Generative Priors for Video Compression
Yinhuan Huang, Jingkai Ying, Pu Chen +1
Under stringent bitrate constraints, existing video codecs struggle to balance source fidelity and perceptual realism. Distortion-oriented codecs often oversmooth details, while ge…
eess.SP2026
Token Communication for Multimodal Large Language Model
Jingkai Ying, Zhijin Qin, Yuan Shen +1
With the broad success of the Transformer architecture, token is becoming a new basic information processing unit. This trend is especially evident in multimodal large language mod…
eess.SP2026
Distribution-Aware Constellation Learning for Image Transmission
Xufeng Zhang, Yinhuan Huang, Jingkai Ying +2
Semantic communication has demonstrated significant potential for image transmission, especially in bandwidth-limited and low signal-to-noise ratio scenarios. However, most existin…