Amanpreet Singh

is this you? claim profile

∙ 0 followers
NYU college ∙ Stony Brook University

Transformer is All You Need: Multimodal Multitask Learning with a Unified Transformer

We propose UniT, a Unified Transformer model to simultaneously learn the...
02/22/2021 ∙ by Ronghang Hu, et al. ∙ 42 ∙ share

read it
Open4Business(O4B): An Open Access Dataset for Summarizing Business Documents

A major challenge in fine-tuning deep learning models for automatic summ...
11/15/2020 ∙ by Amanpreet Singh, et al. ∙ 13 ∙ share

read it
Seeing the Un-Scene: Learning Amodal Semantic Maps for Room Navigation

We introduce a learning-based approach for room navigation using semanti...
07/20/2020 ∙ by Medhini Narasimhan, et al. ∙ 2 ∙ share

read it
The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes

This work proposes a new challenge set for multimodal classification, fo...
05/10/2020 ∙ by Douwe Kiela, et al. ∙ 7 ∙ share

read it
Are we pretraining it right? Digging deeper into visio-linguistic pretraining

Numerous recent works have proposed pretraining generic visio-linguistic...
04/19/2020 ∙ by Amanpreet Singh, et al. ∙ 1 ∙ share

read it
TextCaps: a Dataset for Image Captioning with Reading Comprehension

Image descriptions can help visually impaired people to quickly understa...
03/24/2020 ∙ by Oleksii Sidorov, et al. ∙ 0 ∙ share

read it
Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQA

Many visual scenes contain text that carries crucial information, and it...
11/14/2019 ∙ by Ronghang Hu, et al. ∙ 22 ∙ share

read it
SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems

In the last year, new models and methods for pretraining and transfer le...
05/02/2019 ∙ by Alex Wang, et al. ∙ 4 ∙ share

read it
Towards VQA Models that can Read

Studies have shown that a dominant class of questions asked by visually ...
04/18/2019 ∙ by Amanpreet Singh, et al. ∙ 12 ∙ share

read it
Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future

In model-based reinforcement learning, the agent interleaves between mod...
03/05/2019 ∙ by Nan Rosemary Ke, et al. ∙ 14 ∙ share

read it
Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks

Learning when to communicate and doing that effectively is essential in ...
12/23/2018 ∙ by Amanpreet Singh, et al. ∙ 0 ∙ share

read it
CanvasGAN: A simple baseline for text to image generation by incrementally patching a canvas

We propose a new recurrent generative model for generating images from t...
10/05/2018 ∙ by Amanpreet Singh, et al. ∙ 0 ∙ share

read it
Neural Network Acceptability Judgments

In this work, we explore the ability of artificial neural networks to ju...
05/31/2018 ∙ by Alex Warstadt, et al. ∙ 0 ∙ share

read it
Building a Structured Query Engine

Finding patterns in data and being able to retrieve information from tho...
10/02/2017 ∙ by Amanpreet Singh, et al. ∙ 0 ∙ share

read it

Amanpreet Singh

Featured Co-authors

Yoshua Bengio

Trevor Darrell

Devi Parikh

Dhruv Batra

Marcus Rohrbach

Samuel R. Bowman

Douwe Kiela

Omer Levy

Anirudh Goyal

Xinlei Chen

Felix Hill

Transformer is All You Need: Multimodal Multitask Learning with a Unified Transformer

Open4Business(O4B): An Open Access Dataset for Summarizing Business Documents

Seeing the Un-Scene: Learning Amodal Semantic Maps for Room Navigation

The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes

Are we pretraining it right? Digging deeper into visio-linguistic pretraining

TextCaps: a Dataset for Image Captioning with Reading Comprehension

Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQA

SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems

Towards VQA Models that can Read

Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future

Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks

CanvasGAN: A simple baseline for text to image generation by incrementally patching a canvas

Neural Network Acceptability Judgments

Building a Structured Query Engine