scispace - formally typeset
O

Oriol Vinyals

Researcher at Google

Publications -  218
Citations -  121048

Oriol Vinyals is an academic researcher from Google. The author has contributed to research in topics: Artificial neural network & Reinforcement learning. The author has an hindex of 84, co-authored 200 publications receiving 82365 citations. Previous affiliations of Oriol Vinyals include University of California, San Diego & University of California, Berkeley.

Papers
More filters
Posted Content

Solving Mixed Integer Programs Using Neural Networks

TL;DR: In this paper, Neural Diving and Neural Branching are applied to the two key sub-tasks of a mixed integer programming (MIP) solver, generating a high-quality joint variable assignment and bounding the gap in objective value between that assignment and an optimal one.
Patent

Processing sequences using convolutional neural networks

TL;DR: In this paper, a method for generating neural network output from an input sequence is proposed, where the output subnetwork is configured to receive the alternative representations and to process the alternative representation to generate the neural network outputs.
Proceedings Article

General-purpose, long-context autoregressive modeling with Perceiver AR

TL;DR: Perceiver AR is developed, an modality-agnostic architecture which uses cross-attention to map long-range inputs to a small number of latents while also maintaining end-to-end causal masking, enabling practical long-context density estimation without the need for hand-crafted sparsity patterns or memory mechanisms.
Posted Content

Video Pixel Networks

TL;DR: The Video Pixel Network (VPN) as discussed by the authors estimates the discrete joint distribution of the raw pixel values in a video by encoding the time, space and color structure of video tensors and encode it as a four-dimensional dependency chain.
Proceedings ArticleDOI

Live speaker identification in conversations

TL;DR: The following article describes the technical demonstration of an online speaker identification system for conversations able to identify the current speaker independent of spoken text or language with a latency of about 1.5 seconds and an accuracy of about 85% (as evaluated against the NIST RT benchmark).