Onboard satellites must restore a channel-degraded image on a few watts, using neuromorphic accelerators (e.g., BrainChip Akida, Intel Loihi-2) that support no softmax or attention. We ask which encoder restores best under that constraint and introduce LIMODENet (LinearMix-ODENet), a 0.69M softmax-/QKV-free backbone wh...
Thanh-Dung Le, V. N. Ha, T. Nguyen et al.· 0 citations
Simulation results show that learning-based access selection substantially reduces the QoS-failure rate compared with signal-based and historical-QoS heuristic methods, and demonstrate the potential of federated QoS-risk learning for reliable, data-local access selection in dynamic wireless environments.
Thieu Van Nguyen, T. Nguyen, Ons Aouedi et al.· IEEE International Symposium...· 0 citations
While Mixture-of-Experts (MoE) models effectively scale model capacity through sparse activation, their deployment is often bottlenecked by prohibitive memory requirements. Extracting a compact subset of experts presents a promising solution. However, existing expert selection heuristics predominantly rely on Top-k ran...
Zheng Lin, Shao-Ke Fang, Yu-Xin Zhang et al.· 0 citations
Experimental results on heterogeneous MNIST and CIFAR-10 settings show that QEF-GT-AdamW consistently improves robustness and convergence performance over representative DecL baselines while achieving favorable accuracy-communication trade-offs under limited wireless resources.
Thieu Van Nguyen, T. Nguyen, Ons Aouedi et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
