Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
Unsupervised Deep Embedding for Clustering Analysis
Clustering is central to many data-driven application domains and has been studied extensively in terms of distance functions and grouping algorithms. Relatively little work has focused on learning…
"What happens if..." Learning to Predict the Effect of Forces in Images
What happens if one pushes a cup sitting on a table toward the edge of the table? How about pushing a desk against a wall? In this paper, we study the problem of understanding the movements of…
What's in an Explanation? Characterizing Knowledge and Inference Requirements for Elementary Science Exams
QA systems have been making steady advances in the challenging elementary science exam domain. In this work, we develop an explanation-based analysis of knowledge and inference requirements, which…
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. In Binary-Weight-Networks, the filters are approximated with binary…
You Only Look Once: Unified, Real-Time Object Detection
We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to…
AI assisted ethics
The growing number of 'smart' instruments, those equipped with AI, has raised concerns because these instruments make autonomous decisions; that is, they act beyond the guidelines provided them by…
Neural AMR: Sequence-to-Sequence Models for Parsing and Generation
Sequence-to-sequence models have shown strong performance across a broad range of applications. However, their application to parsing and generating text using Abstract Meaning Representation (AMR)…
My Computer is an Honor Student — but how Intelligent is it? Standardized Tests as a Measure of AI
Given the well-known limitations of the Turing Test, there is a need for objective tests to both focus attention on, and measure progress towards, the goals of AI. In this paper we argue that…
Closing the Gap Between Short and Long XORs for Model Counting
Many recent algorithms for approximate model counting are based on a reduction to combinatorial searches over random subsets of the space defined by parity or XOR constraints. Long parity…
Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions
What capabilities are required for an AI system to pass standard 4th Grade Science Tests? Previous work has examined the use of Markov Logic Networks (MLNs) to represent the requisite background…