184 citations · 270 across the 14 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.CL2023
Fast Multipole Attention: A Scalable Multilevel Attention Mechanism for Text and Images
Yanming Kang, Giang Tran, Hans De Sterck
While Transformer networks benefit from a global receptive field, their quadratic cost relative to sequence length restricts their application to long sequences and high-resolution…
stat.ML2023
Generalization Bound for Diffusion Models using Random Features
Esha Saha, Giang Tran
Diffusion probabilistic models have been successfully used to generate data from noise. However, most diffusion models are computationally expensive and difficult to interpret with…