Sam Gross
YOU?
Author Swipe
View article: Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching
Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching Open
Bienvenidos to the proceedings of the fifth edition of the workshop on computational approaches for linguistic code-switching (CALCS-2021)!Code-switching is this very interesting phenomenon where multilingual speakers communicate by moving…
View article: Residual Energy-Based Models for Text
Residual Energy-Based Models for Text Open
Current large-scale auto-regressive language models display impressive fluency and can generate convincing text. In this work we start by asking the question: Can the generations of these models be reliably distinguished from real text by …
View article: Energy-Based Models for Text
Energy-Based Models for Text Open
Current large-scale auto-regressive language models display impressive fluency and can generate convincing text. In this work we start by asking the question: Can the generations of these models be reliably distinguished from real text by …
View article: PyTorch: An Imperative Style, High-Performance Deep Learning Library
PyTorch: An Imperative Style, High-Performance Deep Learning Library Open
Deep learning frameworks have often focused on either usability or speed, but not both. PyTorch is a machine learning library that shows that these two goals are in fact compatible: it provides an imperative and Pythonic programming style …
View article: Real or Fake? Learning to Discriminate Machine from Human Generated Text
Real or Fake? Learning to Discriminate Machine from Human Generated Text Open
Energy-based models (EBMs), a.k.a. un-normalized models, have had recent successes in continuous spaces. However, they have not been successfully applied to model text sequences. While decreasing the energy at training samples is straightf…
View article: fairseq: A Fast, Extensible Toolkit for Sequence Modeling
fairseq: A Fast, Extensible Toolkit for Sequence Modeling Open
fairseq is an open-source sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling, and other text generation tasks. The toolkit is based on PyTorch and suppo…
View article: fairseq: A Fast, Extensible Toolkit for Sequence Modeling
fairseq: A Fast, Extensible Toolkit for Sequence Modeling Open
Myle Ott, Sergey Edunov, Alexei Baevski, Angela Fan, Sam Gross, Nathan Ng, David Grangier, Michael Auli. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations). 20…
View article: Deep Counterfactual Regret Minimization
Deep Counterfactual Regret Minimization Open
Counterfactual Regret Minimization (CFR) is the leading framework for solving large imperfect-information games. It converges to an equilibrium by iteratively traversing the game tree. In order to deal with extremely large games, abstracti…
View article: Hard Mixtures of Experts for Large Scale Weakly Supervised Vision
Hard Mixtures of Experts for Large Scale Weakly Supervised Vision Open
Training convolutional networks (CNN's) that fit on a single GPU with minibatch stochastic gradient descent has become effective in practice. However, there is still no effective method for training large CNN's that do not fit in the memor…
View article: Creating a universal SNP and small indel variant caller with deep neural networks
Creating a universal SNP and small indel variant caller with deep neural networks Open
Next-generation sequencing (NGS) is a rapidly evolving set of technologies that can be used to determine the sequence of an individual’s genome 1 by calling genetic variants present in an individual using billions of short, errorful sequen…
View article: Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks
Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks Open
We introduce a simple semi-supervised learning approach for images based on in-painting using an adversarial loss. Images with random patches removed are presented to a generator whose task is to fill in the hole, based on the surrounding …
View article: Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks
Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks Open
We introduce a simple semi-supervised learning approach for images based on in-painting using an adversarial loss. Images with random patches removed are presented to a generator whose task is to fill in the hole, based on the surrounding …
View article: Learning Physical Intuition of Block Towers by Example
Learning Physical Intuition of Block Towers by Example Open
Wooden blocks are a common toy for infants, allowing them to develop motor skills and gain intuition about the physical behavior of the world. In this paper, we explore the ability of deep feed-forward models to learn such intuitive physic…
View article: A MultiPath Network for Object Detection
A MultiPath Network for Object Detection Open
The recent COCO object detection dataset presents several new challenges for object detection. In particular, it contains objects at a broad range of scales, less prototypical images, and requires more precise localization. To address thes…