no code implementations • 1 Mar 2024 • Xiaqiang Tang, Weigao Sun, Siyuan Hu, Yiyang Sun, Yafeng Guo
In the training stage, the motion prediction task under differentiated scenes is abstracted as a multi-task learning problem, an evolutionary algorithm is designed to encourage the network search of the optimal parameters for each scene while sharing common knowledge between different scenes.
no code implementations • 7 Mar 2023 • David Berthelot, Arnaud Autef, Jierui Lin, Dian Ang Yap, Shuangfei Zhai, Siyuan Hu, Daniel Zheng, Walter Talbot, Eric Gu
Denoising Diffusion models have demonstrated their proficiency for generative sampling.
no code implementations • 25 May 2021 • Siyuan Hu, Stephen Jordan, Rasim Boyacioglu, Ignacio Rozada, Matthias Troyer, Mark Griswold, Debra McGivney, Dan Ma
During optimization, the spatial response function is independent of sequence design and does not need to be recalculated.