Publications (17)
Smaller, Faster, Cheaper: Architectural Designs for Efficient Machine Learning
Steven Walton
Major advancements in the capabilities of computer vision models have been primarily fueled by rapid expansion of datasets, model parameters, and computational budgets, leading to…
Generalized Neighborhood Attention: Multi-dimensional Sparse Attention at the Speed of Light
Ali Hassani, Fengzhe Zhou, Aditya Kane +13
Many sparse attention mechanisms such as Neighborhood Attention have typically failed to consistently deliver speedup over the self attention baseline. This is largely due to the l…
ConvMLP: Hierarchical Convolutional MLPs for Vision
Jiachen Li, Ali Hassani, Steven Walton +1
MLP-based architectures, which consist of a sequence of consecutive multi-layer perceptron blocks, have recently been found to reach comparable results to convolutional and transfo…
Escaping the Big Data Paradigm with Compact Transformers
Ali Hassani, Steven Walton, Nikhil Shah +3
With the rise of Transformers as the standard for language processing, and their advancements in computer vision, there has been a corresponding growth in parameter size and amount…
Neighborhood Attention Transformer
Ali Hassani, Steven Walton, Jiachen Li +2
We present Neighborhood Attention (NA), the first efficient and scalable sliding-window attention mechanism for vision. NA is a pixel-wise operation, localizing self attention (SA)…
ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models
Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma +31
Large Multimodal Models (LMMs) exhibit shortfalls when interpreting images and, by some measures, have poorer spatial cognition than young children or animals. Despite this, they a…