About

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Datasets

Latest papers with code

Lossless Compression with Latent Variable Models

21 Apr 2021j-towns/craystack

We develop a simple and elegant method for lossless compression using latent variable models, which we call 'bits back with asymmetric numeral systems' (BB-ANS).

LATENT VARIABLE MODELS

42
21 Apr 2021

GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement

20 Apr 2021applied-ai-lab/genesis

Moreover, object representations are often inferred using RNNs which do not scale well to large images or iterative refinement which avoids imposing an unnatural ordering on objects in an image but requires the a priori initialisation of a fixed number of object representations.

IMAGE GENERATION LATENT VARIABLE MODELS REPRESENTATION LEARNING SCENE GENERATION SEMANTIC SEGMENTATION UNSUPERVISED IMAGE SEGMENTATION UNSUPERVISED OBJECT SEGMENTATION

37
20 Apr 2021

Comparing the Value of Labeled and Unlabeled Data in Method-of-Moments Latent Variable Estimation

3 Mar 2021bencw99/comparing-labeled-and-unlabeled-data

We apply our decomposition framework to three scenarios -- well-specified, misspecified, and corrected models -- to 1) choose between labeled and unlabeled data and 2) learn from their combination.

LATENT VARIABLE MODELS

1
03 Mar 2021

Meta-Learning with Variational Bayes

3 Mar 2021lucaslingle/metavb

At the heart of our contribution is a new result, showing that for a broad class of deep generative latent variable models, the relevant VB updates do not depend on any generative neural network.

LATENT VARIABLE MODELS META-LEARNING

0
03 Mar 2021

Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting

28 Jan 2021zalandoresearch/pytorch-ts

In this work, we propose \texttt{TimeGrad}, an autoregressive model for multivariate probabilistic time series forecasting which samples from the data distribution at each time step by estimating its gradient.

LATENT VARIABLE MODELS MULTIVARIATE TIME SERIES FORECASTING PROBABILISTIC TIME SERIES FORECASTING TIME SERIES

368
28 Jan 2021

Transformer-based Conditional Variational Autoencoder for Controllable Story Generation

4 Jan 2021fangleai/TransformerCVAE

In this paper, we advocate to revive latent variable modeling, essentially the power of representation learning, in the era of Transformers to enhance controllability without hurting state-of-the-art generation effectiveness.

LATENT VARIABLE MODELS REPRESENTATION LEARNING

17
04 Jan 2021

Learning Informative Representations of Biomedical Relations with Latent Variable Models

20 Nov 2020BenevolentAI/RELVM

In both cases, recent methods have achieved strong results by learning a point estimate to represent the relation; this is then used as the input to a relation classifier.

LATENT VARIABLE MODELS RELATION EXTRACTION

5
20 Nov 2020

Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAE

NeurIPS 2020 zhd96/pi-vae

Specifically, we propose to construct latent variable models of neural activity while simultaneously modeling the relation between the latent and task variables (non-neural variables, e. g. sensory, motor, and other externally observable states).

HIPPOCAMPUS LATENT VARIABLE MODELS

6
09 Nov 2020

Diverse Image Captioning with Context-Object Split Latent Spaces

NeurIPS 2020 visinf/cos-cvae

Our framework not only enables diverse captioning through context-based pseudo supervision, but extends this to images with novel objects and without paired captions in the training data.

IMAGE CAPTIONING LATENT VARIABLE MODELS

19
02 Nov 2020

Toward a Generalization Metric for Deep Generative Models

2 Nov 2020htt210/GeneralizationMetricGAN

In this paper, we investigate the capacity of these metrics in measuring the generalization capacity.

LATENT VARIABLE MODELS

3
02 Nov 2020