
-
Do Transformer Modifications Transfer Across Implementations and Applications?
The research community has proposed copious modifications to the Transfo...
read it
-
NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
We review the EfficientQA competition from NeurIPS 2020. The competition...
read it
-
Extracting Training Data from Large Language Models
It has become common to publish large (billion parameter) language model...
read it
-
mT5: A massively multilingual pre-trained text-to-text transformer
The recent "Text-to-Text Transfer Transformer" (T5) leveraged a unified ...
read it
-
WT5?! Training Text-to-Text Models to Explain their Predictions
Neural networks have recently achieved human-level performance on variou...
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...
read it
-
DDSP: Differentiable Digital Signal Processing
Most generative models of audio directly generate samples in one of two ...
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...
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...
read it
-
Learning to Groove with Inverse Sequence Transformations
We explore models for translating abstract musical ideas (scores, rhythm...
read it
-
Counterpoint by Convolution
Machine learning models of music typically break up the task of composit...
read it
-
GANSynth: Adversarial Neural Audio Synthesis
Efficient audio synthesis is an inherently difficult machine learning ta...
read it
-
Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset
Generating musical audio directly with neural networks is notoriously di...
read it
-
Learning a Latent Space of Multitrack Measures
Discovering and exploring the underlying structure of multi-instrumental...
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...
read it
-
Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models
Deep generative neural networks have proven effective at both conditiona...
read it
-
Onsets and Frames: Dual-Objective Piano Transcription
We consider the problem of transcribing polyphonic piano music with an e...
read it
-
Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
Generative models in vision have seen rapid progress due to algorithmic ...
read it