Petuum, Inc.

∙ Pittsburgh , United States ∙ 0 followers

Petuum, Inc. is a startup building a revolutionary artificial intelligence (AI) and machine learning (ML) solution development platform.

Stackelberg GAN: Towards Provable Minimax Equilibrium via Multi-Generator Architectures

We study the problem of alleviating the instability issue in the GAN tra...
11/19/2018 ∙ by Hongyang Zhang, et al. ∙ 8 ∙ share

read it
Knowledge-driven Encode, Retrieve, Paraphrase for Medical Image Report Generation

Generating long and semantic-coherent reports to describe medical images...
03/25/2019 ∙ by Christy Y. Li, et al. ∙ 8 ∙ share

read it
Toward Unsupervised Text Content Manipulation

Controlled generation of text is of high practical use. Recent efforts h...
01/28/2019 ∙ by Wentao Wang, et al. ∙ 6 ∙ share

read it
Deep Generative Models with Learnable Knowledge Constraints

The broad set of deep generative models (DGMs) has achieved remarkable a...
06/26/2018 ∙ by Zhiting Hu, et al. ∙ 4 ∙ share

read it
Learning Less-Overlapping Representations

In representation learning (RL), how to make the learned representations...
11/25/2017 ∙ by Pengtao Xie, et al. ∙ 0 ∙ share

read it
Diversity-Promoting Bayesian Learning of Latent Variable Models

To address three important issues involved in latent variable models (LV...
11/23/2017 ∙ by Pengtao Xie, et al. ∙ 0 ∙ share

read it
On the Automatic Generation of Medical Imaging Reports

Medical imaging is widely used in clinical practice for diagnosis and tr...
11/22/2017 ∙ by Baoyu Jing, et al. ∙ 0 ∙ share

read it
On Unifying Deep Generative Models

Deep generative models have achieved impressive success in recent years....
06/02/2017 ∙ by Zhiting Hu, et al. ∙ 0 ∙ share

read it
Dual Motion GAN for Future-Flow Embedded Video Prediction

Future frame prediction in videos is a promising avenue for unsupervised...
08/01/2017 ∙ by Xiaodan Liang, et al. ∙ 0 ∙ share

read it
ZM-Net: Real-time Zero-shot Image Manipulation Network

Many problems in image processing and computer vision (e.g. colorization...
03/21/2017 ∙ by Hao Wang, et al. ∙ 0 ∙ share

read it
SCAN: Structure Correcting Adversarial Network for Organ Segmentation in Chest X-rays

Chest X-ray (CXR) is one of the most commonly prescribed medical imaging...
03/26/2017 ∙ by Wei Dai, et al. ∙ 0 ∙ share

read it
Effective Use of Bidirectional Language Modeling for Medical Named Entity Recognition

Biomedical named entity recognition (NER) is a fundamental task in text ...
11/21/2017 ∙ by Devendra Singh Sachan, et al. ∙ 0 ∙ share

read it
Dynamic-structured Semantic Propagation Network

Semantic concept hierarchy is still under-explored for semantic segmenta...
03/16/2018 ∙ by Xiaodan Liang, et al. ∙ 0 ∙ share

read it
Parameter Sharing Methods for Multilingual Self-Attentional Translation Models

In multilingual neural machine translation, it has been shown that shari...
09/01/2018 ∙ by Devendra Singh Sachan, et al. ∙ 0 ∙ share

read it
Unsupervised Pseudo-Labeling for Extractive Summarization on Electronic Health Records

Extractive summarization is very useful for physicians to better manage ...
11/20/2018 ∙ by Xiangan Liu, et al. ∙ 0 ∙ share

read it
Connecting the Dots Between MLE and RL for Sequence Generation

Sequence generation models such as recurrent networks can be trained wit...
11/24/2018 ∙ by Bowen Tan, et al. ∙ 0 ∙ share

read it
Target-Guided Open-Domain Conversation

Many real-world open-domain conversation applications have specific goal...
05/28/2019 ∙ by Jianheng Tang, et al. ∙ 0 ∙ share

read it

Petuum, Inc.

Featured Researchers

Eric P Xing

Hao Zhang

Eric Xing

Pengtao Xie

Wei Dai

Devendra Singh Sachan

Nanqing Dong

Baoyu Jing

Hongbao Zhang

Joseph Doyle

Xiangan Liu

Stackelberg GAN: Towards Provable Minimax Equilibrium via Multi-Generator Architectures

Knowledge-driven Encode, Retrieve, Paraphrase for Medical Image Report Generation

Toward Unsupervised Text Content Manipulation

Deep Generative Models with Learnable Knowledge Constraints

Learning Less-Overlapping Representations

Diversity-Promoting Bayesian Learning of Latent Variable Models

On the Automatic Generation of Medical Imaging Reports

On Unifying Deep Generative Models

Dual Motion GAN for Future-Flow Embedded Video Prediction

ZM-Net: Real-time Zero-shot Image Manipulation Network

SCAN: Structure Correcting Adversarial Network for Organ Segmentation in Chest X-rays

Effective Use of Bidirectional Language Modeling for Medical Named Entity Recognition

Dynamic-structured Semantic Propagation Network

Parameter Sharing Methods for Multilingual Self-Attentional Translation Models

Unsupervised Pseudo-Labeling for Extractive Summarization on Electronic Health Records

Connecting the Dots Between MLE and RL for Sequence Generation

Target-Guided Open-Domain Conversation