UAVM achieves a new state-of-the-art audio-visual event classification accuracy of 65.8% on VGGSound. 

Multipool is a high-resolution genetic mapping for pooled sequencing.

A Caffe-based deep learning platform with automatic hyper-parameter searching.

PRESCIENT is a generative model for modeling single-cell time-series.

Active Buffer Management in Datacenters.

Var-CNN is a data-efficient website fingerprinting attack based on deep learning.

OpenTuner is a new framework for building domain-specific multi-objective program autotuners. OpenTuner supports fully customizable configuration representations, an extensible technique representation to allow for domain-specific techniques, and an easy to use interface for communicating with the tuned program.

This repository contains the code used for the following paper: Improving Neural Language Models by Segmenting, Attending, and Predicting the Future.

This repository contains code for reproducing the results of Combining Diverse Feature Priors