1 code implementation • 12 Oct 2022 • Eric Nguyen, Karan Goel, Albert Gu, Gordon W. Downs, Preey Shah, Tri Dao, Stephen A. Baccus, Christopher Ré
On ImageNet-1k, S4ND exceeds the performance of a Vision Transformer baseline by $1. 5\%$ when training with a $1$D sequence of patches, and matches ConvNeXt when modeling images in $2$D.
no code implementations • 29 Apr 2021 • Preey Shah, Aman Bansal, S. Akshay, Supratik Chakraborty
Additionally, a specification admits a polynomial-sized functional solution iff there exists a semantically equivalent polynomial-sized SAUNF representation.
no code implementations • 28 Jan 2021 • Aman Bansal, Preey Shah, Sahil Shah
It demonstrates properties and usage of data structures in a general environment, thereby helping in learning, logical debugging, and code comprehension.
Computers and Society