research
∙
06/02/2021
Decision Transformer: Reinforcement Learning via Sequence Modeling
We present a framework that abstracts Reinforcement Learning (RL) as a s...
share
research
∙
04/20/2021
VideoGPT: Video Generation using VQ-VAE and Transformers
We present VideoGPT: a conceptually simple architecture for scaling like...
research
∙
03/23/2021
Scaling Local Self-Attention For Parameter Efficient Visual Backbones
Self-attention has the promise of improving computer vision systems due ...
research
∙
03/13/2021
Revisiting ResNets: Improved Training and Scaling Strategies
Novel computer vision architectures monopolize the spotlight, but the im...
research
∙
03/04/2021
Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings
Recent advances in off-policy deep reinforcement learning (RL) have led ...
research
∙
01/27/2021
Bottleneck Transformers for Visual Recognition
We present BoTNet, a conceptually simple yet powerful backbone architect...
research
∙
12/13/2020
Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation
Building instance segmentation models that are data-efficient and can ha...
research
∙
10/19/2020
D2RL: Deep Dense Architectures in Reinforcement Learning
While improvements in deep learning architectures have played a crucial ...
research
∙
09/16/2020
Evaluating Self-Supervised Pretraining Without Using Labels
A common practice in unsupervised representation learning is to use labe...
research
∙
07/09/2020
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning
Model-free deep reinforcement learning (RL) has been successful in a ran...
research
∙
04/30/2020
Reinforcement Learning with Augmented Data
Learning from visual observations is a fundamental yet challenging probl...
research
∙
04/08/2020
CURL: Contrastive Unsupervised Representations for Reinforcement Learning
We present CURL: Contrastive Unsupervised Representations for Reinforcem...
research
∙
02/01/2019
Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design
Flow-based generative models are powerful exact likelihood models with e...
research
∙
04/02/2018
