Adam Roberts

is this you? claim profile

0 followers
Google

Do Transformer Modifications Transfer Across Implementations and Applications?

The research community has proposed copious modifications to the Transfo...
02/23/2021 ∙ by Sharan Narang, et al. ∙ 10 ∙ share

read it
NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned

We review the EfficientQA competition from NeurIPS 2020. The competition...
01/01/2021 ∙ by Sewon Min, et al. ∙ 15 ∙ share

read it
Extracting Training Data from Large Language Models

It has become common to publish large (billion parameter) language model...
12/14/2020 ∙ by Nicholas Carlini, et al. ∙ 0 ∙ share

read it
mT5: A massively multilingual pre-trained text-to-text transformer

The recent "Text-to-Text Transfer Transformer" (T5) leveraged a unified ...
10/22/2020 ∙ by Linting Xue, et al. ∙ 0 ∙ share

read it
WT5?! Training Text-to-Text Models to Explain their Predictions

Neural networks have recently achieved human-level performance on variou...
04/30/2020 ∙ by Sharan Narang, et al. ∙ 0 ∙ share

read it
How Much Knowledge Can You Pack Into the Parameters of a Language Model?

It has recently been observed that neural language models trained on uns...
02/10/2020 ∙ by Adam Roberts, et al. ∙ 0 ∙ share

read it
DDSP: Differentiable Digital Signal Processing

Most generative models of audio directly generate samples in one of two ...
01/14/2020 ∙ by Jesse Engel, et al. ∙ 11 ∙ share

read it
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

Transfer learning, where a model is first pre-trained on a data-rich tas...
10/23/2019 ∙ by Colin Raffel, et al. ∙ 0 ∙ share

read it
The Bach Doodle: Approachable music composition with machine learning at scale

To make music composition more approachable, we designed the first AI-po...
07/14/2019 ∙ by Cheng-Zhi Anna Huang, et al. ∙ 6 ∙ share

read it
Learning to Groove with Inverse Sequence Transformations

We explore models for translating abstract musical ideas (scores, rhythm...
05/14/2019 ∙ by Jon Gillick, et al. ∙ 0 ∙ share

read it
Counterpoint by Convolution

Machine learning models of music typically break up the task of composit...
03/18/2019 ∙ by Cheng-Zhi Anna Huang, et al. ∙ 0 ∙ share

read it
GANSynth: Adversarial Neural Audio Synthesis

Efficient audio synthesis is an inherently difficult machine learning ta...
02/23/2019 ∙ by Jesse Engel, et al. ∙ 20 ∙ share

read it
Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset

Generating musical audio directly with neural networks is notoriously di...
10/29/2018 ∙ by Curtis Hawthorne, et al. ∙ 0 ∙ share

read it
Learning a Latent Space of Multitrack Measures

Discovering and exploring the underlying structure of multi-instrumental...
06/01/2018 ∙ by Ian Simon, et al. ∙ 0 ∙ share

read it
A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music

The Variational Autoencoder (VAE) has proven to be an effective model fo...
03/13/2018 ∙ by Adam Roberts, et al. ∙ 0 ∙ share

read it
Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models

Deep generative neural networks have proven effective at both conditiona...
11/15/2017 ∙ by Jesse Engel, et al. ∙ 0 ∙ share

read it
Onsets and Frames: Dual-Objective Piano Transcription

We consider the problem of transcribing polyphonic piano music with an e...
10/30/2017 ∙ by Curtis Hawthorne, et al. ∙ 0 ∙ share

read it
Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders

Generative models in vision have seen rapid progress due to algorithmic ...
04/05/2017 ∙ by Jesse Engel, et al. ∙ 0 ∙ share

read it

Adam Roberts

Featured Co-authors

Jianfeng Gao

Wei Li

Aaron Courville

Dawn Song

Sebastian Riedel

Hannaneh Hajishirzi

Mohammad Norouzi

Karen Simonyan

Yi Tay

Xiaodong Liu

Edouard Grave

Do Transformer Modifications Transfer Across Implementations and Applications?

NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned

Extracting Training Data from Large Language Models

mT5: A massively multilingual pre-trained text-to-text transformer

WT5?! Training Text-to-Text Models to Explain their Predictions

How Much Knowledge Can You Pack Into the Parameters of a Language Model?

DDSP: Differentiable Digital Signal Processing

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

The Bach Doodle: Approachable music composition with machine learning at scale

Learning to Groove with Inverse Sequence Transformations

Counterpoint by Convolution

GANSynth: Adversarial Neural Audio Synthesis

Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset

Learning a Latent Space of Multitrack Measures

A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music

Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models

Onsets and Frames: Dual-Objective Piano Transcription

Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders