activity
20212023
most citedScaling Vision Transformers to 22 Billion Parameters

118 citations · 144 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV20238 cited

Replacing softmax with ReLU in Vision Transformers

Mitchell Wortsman, Jaehoon Lee, Justin Gilmer +1

Previous research observed accuracy degradation when replacing the attention softmax with a point-wise activation such as ReLU. In the context of vision transformers, we find that…

cs.LG20234 cited

Small-scale proxies for large-scale Transformer training instabilities

Mitchell Wortsman, Peter J. Liu, Lechao Xiao +13

Teams that have trained large Transformer-based models have reported training instabilities at large scale that did not appear when training with the same hyperparameters at smalle…

cs.CV2023118 cited

Scaling Vision Transformers to 22 Billion Parameters

Mostafa Dehghani, Josip Djolonga, Basil Mustafa +39

The scaling of Transformers has driven breakthrough capabilities for language models. At present, the largest large language models (LLMs) contain upwards of 100B parameters. Visio…

cs.LG202312 cited

Improving Training Stability for Multitask Ranking Models in Recommender Systems

Jiaxi Tang, Yoel Drori, Daryl Chang +6

Recommender systems play an important role in many content platforms. While most recommendation research is dedicated to designing better models to improve user experience, we foun…

cs.LG20222 cited

Pre-training helps Bayesian optimization too

Zi Wang, George E. Dahl, Kevin Swersky +6

Bayesian optimization (BO) has become a popular strategy for global optimization of many expensive real-world functions. Contrary to a common belief that BO is suited to optimizing…

cs.LG2021

Predicting the utility of search spaces for black-box optimization: a simple, budget-aware approach

Setareh Ariafar, Justin Gilmer, Zachary Nado +3

Black box optimization requires specifying a search space to explore for solutions, e.g. a d-dimensional compact space, and this choice is critical for getting the best results at…