J
Jakob Uszkoreit
Researcher at Google
Publications - 85
Citations - 83076
Jakob Uszkoreit is an academic researcher from Google. The author has contributed to research in topics: Machine translation & Transformer (machine learning model). The author has an hindex of 36, co-authored 84 publications receiving 37432 citations. Previous affiliations of Jakob Uszkoreit include University of California, Berkeley.
Papers
More filters
Patent
Parallel decoding using auto-regression machine learning model
TL;DR: In this article, the authors proposed a method, system, and device for generating output from auto-regression to a sequence model in a parallel mode, including computer program encoded in a computer storing medium.
Patent
Multi-task multi-modal machine learning system
Noam Shazeer,Aidan N. Gomez,Lukasz Kaiser,Jakob Uszkoreit,Llion Jones,Niki Parmar,Ashish Vaswani +6 more
TL;DR: In this paper, a machine learning model that includes multiple input modality neural networks corresponding to respective different modalities and being configured to map received data inputs of the corresponding modality to mapped data inputs from a unified representation space is presented.
Patent
Auto-regressive video generation neural networks
TL;DR: In this paper, a method for generating a video including multiple frames, each of the frames having multiple channels, is described, which includes identifying a partitioning of the initial output video into a set of channel slices that are indexed according to a particular slice order.
Funnel Vision Transformer for image classification
Alexey Dosovitskiy,Lucas Beyer,Alexander Kolesnikov,Dirk Weissenborn,Xiaohua Zhai,Thomas Unterthiner,Mostafa Dehghani,Matthias Minderer,Georg Heigold,Sylvain Gelly,Jakob Uszkoreit +10 more
TL;DR: This project examines a similar idea on the ImageNet dataset that gradually shrink the image patch length dimension of Vision Transformer as the layers go deeper, in order to save the computational resources (Funnel-ViT).