Search Results for author:
Found 25 papers, 15 papers with code
A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
Pre-trained large language models (LLMs) have recently achieved better generalization and sample efficiency in autonomous web automation.
PaLM: Scaling Language Modeling with Pathways
To further our understanding of the impact of scale on few-shot learning, we trained a 540-billion parameter, densely activated, Transformer language model, which we call Pathways Language Model PaLM.
Ranked #1 on
Natural Language Inference
on RTE
Deduplicating Training Data Makes Language Models Better
As a result, over 1% of the unprompted output of language models trained on these datasets is copied verbatim from the training data.
Joint Attention for Multi-Agent Coordination and Social Learning
We then train agents to minimize the difference between the attention weights that they apply to the environment at each timestep, and the attention of other agents.
Emergent Social Learning via Multi-agent Reinforcement Learning
We analyze the reasons for this deficiency, and show that by imposing constraints on the training environment and introducing a model-based auxiliary loss we are able to obtain generalized social learning policies which enable agents to: i) discover complex skills that are not learned from single-agent training, and ii) adapt online to novel environments by taking cues from experts present in the new environment.
Toward Better Storylines with Sentence-Level Language Models
We propose a sentence-level language model which selects the next sentence in a story from a finite set of fluent alternatives.
Automatic Detection of Generated Text is Easiest when Humans are Fooled
Recent advancements in neural language modelling make it possible to rapidly generate vast amounts of human-sounding text.
Unsupervised Hierarchical Story Infilling
Story infilling involves predicting words to go into a missing span from a story.
Learning to Groove with Inverse Sequence Transformations
We explore models for translating abstract musical ideas (scores, rhythms) into expressive performances using Seq2Seq and recurrent Variational Information Bottleneck (VIB) models.
A Learned Representation for Scalable Vector Graphics
Dramatic advances in generative models have resulted in near photographic quality for artificially rendered faces, animals and other objects in the natural world.
Counterpoint by Convolution
Machine learning models of music typically break up the task of composition into a chronological process, composing a piece of music in a single pass from beginning to end.
Ranked #4 on
Music Modeling
on JSB Chorales
Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset
Generating musical audio directly with neural networks is notoriously difficult because it requires coherently modeling structure at many different timescales.
Music Transformer
This is impractical for long sequences such as musical compositions since their memory complexity for intermediate relative information is quadratic in the sequence length.
Ranked #3 on
Music Modeling
on JSB Chorales
This Time with Feeling: Learning Expressive Musical Performance
Music generation has generally been focused on either creating scores or interpreting them.
Learning a Latent Space of Multitrack Measures
Discovering and exploring the underlying structure of multi-instrumental music using learning-based approaches remains an open problem.
A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music
The Variational Autoencoder (VAE) has proven to be an effective model for producing semantically meaningful latent representations for natural data.
Learning via social awareness: Improving a deep generative sketching model with facial feedback
We use a Latent Constraints GAN (LC-GAN) to learn from the facial feedback of a small group of viewers, by optimizing the model to produce sketches that it predicts will lead to more positive facial expressions.
Onsets and Frames: Dual-Objective Piano Transcription
We advance the state of the art in polyphonic piano music transcription by using a deep convolutional and recurrent neural network which is trained to jointly predict onsets and frames.
Improving image generative models with human interactions
GANs provide a framework for training generative models which mimic a data distribution.
A Neural Representation of Sketch Drawings
We present sketch-rnn, a recurrent neural network (RNN) able to construct stroke-based drawings of common objects.
Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
Generative models in vision have seen rapid progress due to algorithmic improvements and the availability of high-quality image datasets.
Online and Linear-Time Attention by Enforcing Monotonic Alignments
Recurrent neural network models with an attention mechanism have proven to be extremely effective on a wide variety of sequence-to-sequence problems.
Ranked #20 on
Speech Recognition
on TIMIT
Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control
This paper proposes a general method for improving the structure and quality of sequences generated by a recurrent neural network (RNN), while maintaining information originally learned from data, as well as sample diversity.
An Infinite Factor Model Hierarchy Via a Noisy-Or Mechanism
The Indian Buffet Process is a Bayesian nonparametric approach that models objects as arising from an infinite number of latent factors.
Automatic Generation of Social Tags for Music Recommendation
Social tags are user-generated keywords associated with some resource on the Web.
