
Variational Temporal Abstraction
We introduce a variational approach to learning and inference of tempora...
read it

Scalable ObjectOriented Sequential Generative Models
The main limitation of previous approaches to unsupervised sequential ob...
read it

SPACE: Unsupervised ObjectOriented Scene Representation via Spatial Attention and Decomposition
The ability to decompose complex multiobject scenes into meaningful abs...
read it

Reinforced Imitation in Heterogeneous Action Space
Imitation learning is an effective alternative approach to learn a polic...
read it

Generative Hierarchical Models for Parts, Objects, and Scenes
Compositional structures between parts and objects are inherent in natur...
read it

Sequential Neural Processes
Neural processes combine the strengths of neural networks and Gaussian p...
read it

Neural Multisensory Scene Inference
For embodied agents to infer representations of the underlying 3D physic...
read it

Scalable MCMC for Mixed Membership Stochastic Blockmodels
We propose a stochastic gradient Markov chain Monte Carlo (SGMCMC) algo...
read it

LargeScale Distributed Bayesian Matrix Factorization using Stochastic Gradient MCMC
Despite having various attractive qualities such as high prediction accu...
read it

Bayesian Posterior Sampling via Stochastic Gradient Fisher Scoring
In this paper we address the following question: Can we approximately sa...
read it

A Neural Knowledge Language Model
Current language models have a significant limitation in the ability to ...
read it

Hierarchical Memory Networks
Memory networks are neural networks with an explicit memory component th...
read it

Pointing the Unknown Words
The problem of rare and unknown words is an important issue that can pot...
read it

Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid QuestionAnswer Corpus
Over the past decade, largescale supervised learning corpora have enabl...
read it

Bayesian ModelAgnostic MetaLearning
Learning to infer Bayesian posterior from a fewshot dataset is an impor...
read it

Learning SingleView 3D Reconstruction with Adversarial Training
Singleview 3D shape reconstruction is an important but challenging prob...
read it
Sungjin Ahn
is this you? claim profile