Search Results for author:
Found 3 papers, 1 papers with code
Outlier-Efficient Hopfield Layers for Large Transformer-Based Models
Interestingly, this memory model manifests a model-based interpretation of an outlier-efficient attention mechanism ($\text{Softmax}_1$): it is an approximation of the memory retrieval process of $\mathtt{OutEffHop}$.
Ranked #1 on
Quantization
on Wiki-40B
How to Design Sample and Computationally Efficient VQA Models
In multi-modal reasoning tasks, such as visual question answering (VQA), there have been many modeling and training paradigms tested.
Differentiable End-to-End Program Executor for Sample and Computationally Efficient VQA
We present a differentiable end-to-end program executor (DePe), which addresses Visual Question Answering (VQA) in a sample and computationally efficient manner.
