Space data centers (SpaceDCs) are emerging as platforms for large language models (LLMs), supported by continuous solar-energy harvesting and high-speed interconnections. The mixture-of-experts (MoE) architecture supports distributed LLM inference by deploying experts across satellites. However, skewed expert activatio...
This paper analytically characterize the progressive token-reconstruction error and derive a diffusion-step activation threshold that predicts when SpaceDiffusion is expected to outperform conventional decode-and-forward (DF) relaying, and develops an energy-aware early-exit policy to efficiently deploy SpaceDiffusion...
Jian-Hao Huang, Zhan-Wei Wang, K. Letaief et al.· 0 citations
A framework for solar-powered space generative AI in which a satellite receives a user prompt, executes a diffusion-based image-generation model, and downlinks the compressed result within a strict time window is presented.
Jie-Rui Zhang, Jianhao Huang, Zhanwei Wang et al.· 0 citations
An inference-aware AirMoE error metric is constructed to quantify aggregation distortion effects on end-to-end (E2E) inference accuracy via perturbation-based layer-sensitivity calibration, and an activation- and channel-aware expert placement strategy is developed that assigns more important experts to devices with lo...
