Abstract: Model quantization reduces the bit-width of weights and activations, improving memory efficiency and inference speed in diffusion models. However, achieving 4-bit quantization remains ...
Abstract: Aiming to enhance the robustness and transient performance under model parameter mismatch, this article proposes a self-tuning incremental model-based predictive current control (STIM-PCC) ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback