Streaming large-scale 3D Gaussian Splatting (3DGS) scenes to bandwidth- and memory-constrained clients is an open systems problem. Replacement-based level-of-detail (LOD) pipelines bound client memory but re-transmit overlapping content across levels, wasting 57-62% of bandwidth on redundancy. Vanilla additive streamin...
Zhi-Cheng Liang, Bo-Yan Li, Zi-Jian Cao et al.· Proceedings of the 34th ACM...· 0 citations
This work proposes Communication-efficient Inference Token Exchange (CITE), a decentralized inference-time framework that reduces communication overhead while outperforming state-of-the-art federated baselines in inference accuracy and privacy resilience.
Wei Sun, Zhi-Cheng Liang, Xian-Da Wang et al.· IEEE Transactions on Mobile...· 0 citations
Generative AI assistants are becoming an advertising medium, embedding sponsored content in their answers. This setting departs from classical position auctions in two ways: an ad's click-through rate depends on the passage that hosts it, and because users stop at their first click, earlier ads take clicks from later o...
Jun-Hua Liu, Zhi-Cheng Liang, Ze-Jun Zhang et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.