
Contrastive Reinforcement Learning of Symbolic Reasoning Domains
Abstract symbolic reasoning, as required in domains such as mathematics ...
read it

Question Generation for Adaptive Education
Intelligent and adaptive online education systems aim to make highquali...
read it

Emergent Communication of Generalizations
To build agents that can collaborate effectively with others, recent res...
read it

Improving Compositionality of Neural Networks by Decoding Representations to Inputs
In traditional software programs, we take for granted how easy it is to ...
read it

Language Through a Prism: A Spectral Approach for Multiscale Language Representations
Language exhibits structure at different scales, ranging from subwords t...
read it

Viewmaker Networks: Learning Views for Unsupervised Representation Learning
Many recent methods for unsupervised representation learning involve tra...
read it

A Simple Framework for Uncertainty in Contrastive Learning
Contrastive approaches to representation learning have recently shown gr...
read it

Conditional Negative Sampling for Contrastive Learning of Visual Representations
Recent methods for learning unsupervised visual representations, dubbed ...
read it

On Mutual Information in Contrastive Learning for Visual Representations
In recent years, several unsupervised, "contrastive" learning algorithms...
read it

Investigating Transferability in Pretrained Language Models
While probing is a common technique for identifying knowledge in the rep...
read it

Variational Item Response Theory: Fast, Accurate, and Expressive
Item Response Theory is a ubiquitous algorithm used around the world to ...
read it

Multimodal Generative Models for Compositional Representation Learning
As deep neural networks become more adept at traditional tasks, many of ...
read it

Shaping Visual Representations with Language for Fewshot Classification
Language is designed to convey useful information about the world, thus ...
read it

Generative Grading: Neural Approximate Parsing for Automated Student Feedback
Open access to highquality education is limited by the difficulty of pr...
read it

Variational Estimators for Bayesian Optimal Experimental Design
Bayesian optimal experimental design (BOED) is a principled framework fo...
read it

Variational Bayesian Optimal Experimental Design
Bayesian optimal experimental design (BOED) is a principled framework fo...
read it

Pragmatic inference and visual abstraction enable contextual flexibility during visual communication
Visual modes of communication are ubiquitous in modern life — from maps ...
read it

Lost in Machine Translation: A Method to Reduce Meaning Loss
A desideratum of highquality translation systems is that they preserve ...
read it

Tensor Variable Elimination for Plated Factor Graphs
A wide class of machine learning algorithms can be reduced to variable e...
read it

MetaAmortized Variational Inference and Learning
How can we learn to do probabilistic inference in a way that generalizes...
read it

Bias and Generalization in Deep Generative Models: An Empirical Study
In high dimensional settings, density estimation algorithms rely crucial...
read it

Differentiable Antithetic Sampling for Variance Reduction in Stochastic Variational Inference
Stochastic optimization techniques are standard in variational inference...
read it

Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference
In modern computer science education, massive open online courses (MOOCs...
read it

Pragmatically Informative Image Captioning with CharacterLevel Reference
We combine a neural image captioner with a Rational Speech Acts (RSA) mo...
read it

Multimodal Generative Models for Scalable WeaklySupervised Learning
Multiple modalities often cooccur when describing natural phenomena. Le...
read it

Church: a language for generative models
We introduce Church, a universal language for describing stochastic gene...
read it

The Infinite Latent Events Model
We present the Infinite Latent Events Model, a nonparametric hierarchica...
read it
Noah Goodman
is this you? claim profile