Sainbayar Sukhbaatar

is this you? claim profile

0 followers
Facebook ∙ NYU college ∙ The University of Tokyo

Hash Layers For Large Sparse Models

We investigate the training of sparse layers that use different paramete...
06/08/2021 ∙ by Stephen Roller, et al. ∙ 0 ∙ share

read it
Staircase Attention for Recurrent Processing of Sequences

Attention mechanisms have become a standard tool for sequence modeling t...
06/08/2021 ∙ by Da Ju, et al. ∙ 0 ∙ share

read it
Not All Memories are Created Equal: Learning to Forget by Expiring

Attention mechanisms have shown promising results in sequence modeling t...
05/13/2021 ∙ by Sainbayar Sukhbaatar, et al. ∙ 0 ∙ share

read it
Memory-Augmented Reinforcement Learning for Image-Goal Navigation

In this work, we address the problem of image-goal navigation in the con...
01/13/2021 ∙ by Lina Mezghani, et al. ∙ 15 ∙ share

read it
Learning to Visually Navigate in Photorealistic Environments Without any Supervision

Learning to navigate in a realistic setting where an agent must rely sol...
04/10/2020 ∙ by Lina Mezghani, et al. ∙ 3 ∙ share

read it
Accessing Higher-level Representations in Sequential Transformers with Feedback Memory

Transformers are feedforward networks that can process input tokens in p...
02/21/2020 ∙ by Angela Fan, et al. ∙ 5 ∙ share

read it
Augmenting Self-attention with Persistent Memory

Transformer networks have lead to important progress in language modelin...
07/02/2019 ∙ by Sainbayar Sukhbaatar, et al. ∙ 6 ∙ share

read it
Adaptive Attention Span in Transformers

We propose a novel self-attention mechanism that can learn its optimal a...
05/19/2019 ∙ by Sainbayar Sukhbaatar, et al. ∙ 0 ∙ 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
Learning Goal Embeddings via Self-Play for Hierarchical Reinforcement Learning

In hierarchical reinforcement learning a major challenge is determining ...
11/22/2018 ∙ by Sainbayar Sukhbaatar, et al. ∙ 0 ∙ share

read it
Planning with Arithmetic and Geometric Attributes

A desirable property of an intelligent agent is its ability to understan...
09/06/2018 ∙ by David Folqué, et al. ∙ 10 ∙ share

read it
Composable Planning with Attributes

The tasks that an agent will need to solve often are not known during tr...
03/01/2018 ∙ by Amy Zhang, et al. ∙ 0 ∙ share

read it
Simple Baseline for Visual Question Answering

We describe a very simple bag-of-words baseline for visual question answ...
12/07/2015 ∙ by Bolei Zhou, et al. ∙ 0 ∙ share

read it
MazeBase: A Sandbox for Learning from Games

This paper introduces MazeBase: an environment for simple 2D games, desi...
11/23/2015 ∙ by Sainbayar Sukhbaatar, et al. ∙ 0 ∙ share

read it
End-To-End Memory Networks

We introduce a neural network with a recurrent attention model over a po...
03/31/2015 ∙ by Sainbayar Sukhbaatar, et al. ∙ 0 ∙ share

read it
Training Convolutional Networks with Noisy Labels

The availability of large labeled datasets has allowed Convolutional Net...
06/09/2014 ∙ by Sainbayar Sukhbaatar, et al. ∙ 0 ∙ share

read it
Auto-pooling: Learning to Improve Invariance of Image Features from Image Sequences

Learning invariant representations from images is one of the hardest cha...
01/15/2013 ∙ by Sainbayar Sukhbaatar, et al. ∙ 0 ∙ share

read it

Sainbayar Sukhbaatar

Featured Co-authors

Dhruv Batra

Joan Bruna

Jason Weston

Bolei Zhou

Arthur Szlam

Armand Joulin

Gabriel Synnaeve

Hervé Jégou

Yuandong Tian

Edouard Grave

Rob Fergus

Hash Layers For Large Sparse Models

Staircase Attention for Recurrent Processing of Sequences

Not All Memories are Created Equal: Learning to Forget by Expiring

Memory-Augmented Reinforcement Learning for Image-Goal Navigation

Learning to Visually Navigate in Photorealistic Environments Without any Supervision

Accessing Higher-level Representations in Sequential Transformers with Feedback Memory

Augmenting Self-attention with Persistent Memory

Adaptive Attention Span in Transformers

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

Learning Goal Embeddings via Self-Play for Hierarchical Reinforcement Learning

Planning with Arithmetic and Geometric Attributes

Composable Planning with Attributes

Simple Baseline for Visual Question Answering

MazeBase: A Sandbox for Learning from Games

End-To-End Memory Networks

Training Convolutional Networks with Noisy Labels

Auto-pooling: Learning to Improve Invariance of Image Features from Image Sequences