
-
Parameter-Efficient Transfer Learning with Diff Pruning
While task-specific finetuning of pretrained networks has led to signifi...
read it
-
Sequence-Level Mixed Sample Data Augmentation
Despite their empirical success, neural networks still have difficulty c...
read it
-
PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
Arguably one of the top success stories of deep learning is transfer lea...
read it
-
MicroNet for Efficient Language Modeling
It is important to design compact language models for efficient deployme...
read it
-
Analyzing machine-learned representations: A natural language case study
As modern deep networks become more complex, and get closer to human-lik...
read it
-
Why Build an Assistant in Minecraft?
In this document we describe a rationale for a research program aimed at...
read it
-
CraftAssist: A Framework for Dialogue-enabled Interactive Agents
This paper describes an implementation of a bot assistant in Minecraft, ...
read it
-
The Internals of the Data Calculator
Data structures are critical in any data-driven scenario, but they are n...
read it
-
Latent Alignment and Variational Attention
Neural attention has become central to many state-of-the-art models in n...
read it
-
Evaluating Compositionality in Sentence Embeddings
An important frontier in the quest for human-like AI is compositional se...
read it