1 citations · 2 across the 5 of their papers we have counts for
6 papers
LookupFFN: Making Transformers Compute-lite for CPU inference
Zhanpeng Zeng, Michael Davies, Pranav Pulijala +2
While GPU clusters are the de facto choice for training large deep neural network (DNN) models today, several reasons including ease of workflow, security and cost have led to effo…
Vcc: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens
Zhanpeng Zeng, Cole Hawkins, Mingyi Hong +4
Transformers are central in modern natural language processing and computer vision applications. Despite recent works devoted to reducing the quadratic cost of such models (as a fu…
Multi Resolution Analysis (MRA) for Approximate Self-Attention
Zhanpeng Zeng, Sourav Pal, Jeffery Kline +2
Transformers have emerged as a preferred model for many tasks in natural langugage processing and vision. Recent efforts on training and deploying Transformers more efficiently hav…
On the Versatile Uses of Partial Distance Correlation in Deep Learning
Xingjian Zhen, Zihang Meng, Rudrasis Chakraborty +1
Comparing the functional behavior of neural network models, whether it is a single network over time or two (or more networks) during or post-training, is an essential step in unde…
Deep Unlearning via Randomized Conditionally Independent Hessians
Ronak Mehta, Sourav Pal, Vikas Singh +1
Recent legislation has led to interest in machine unlearning, i.e., removing specific training samples from a predictive model as if they never existed in the training dataset. Unl…
Neural TMDlayer: Modeling Instantaneous flow of features via SDE Generators
Zihang Meng, Vikas Singh, Sathya N. Ravi
We study how stochastic differential equation (SDE) based ideas can inspire new modifications to existing algorithms for a set of problems in computer vision. Loosely speaking, our…