
Locally Masked Convolution for Autoregressive Models
Highdimensional generative models have many applications including imag...
read it

The Hanabi Challenge: A New Frontier for AI Research
From the early days of computing, games have been important testbeds for...
read it

Improving Lesion Segmentation for Diabetic Retinopathy using Adversarial Learning
Diabetic Retinopathy (DR) is a leading cause of blindness in working age...
read it

Mitigating Manipulation in Peer Review via Randomized Reviewer Assignments
We consider three important challenges in conference peer review: (i) re...
read it

Combining Deep Learning and Verification for Precise Object Instance Detection
Deep learning object detectors often return false positives with very hi...
read it

Embodied Multimodal Multitask Learning
Recent efforts on training visual navigation agents conditioned on langu...
read it

Selftraining with Noisy Student improves ImageNet classification
We present a simple selftraining method that achieves 87.4 on ImageNet,...
read it

A Theoretical Analysis of Contrastive Unsupervised Representation Learning
Recent empirical works have successfully used unlabeled data to learn fe...
read it

InteractionAware MultiAgent Reinforcement Learning for Mobile Agents with Individual Goals
In a multiagent setting, the optimal policy of a single agent is largel...
read it

Variational AutoDecoder: Neural Generative Modeling from Partial Data
Learning a generative model from partial data (data with missingness) is...
read it

Emotion Recognition in Conversation: Research Challenges, Datasets, and Recent Advances
Emotion is intrinsic to humans and consequently emotion understanding is...
read it

Transformer Dissection: An Unified Understanding for Transformer's Attention via the Lens of Kernel
Transformer is a powerful architecture that achieves superior performanc...
read it

Learning Spatial Awareness to Improve Crowd Counting
The aim of crowd counting is to estimate the number of people in images ...
read it

Driving in Dense Traffic with ModelFree Reinforcement Learning
Traditional planning and control methods could fail to find a feasible t...
read it

Factorized Multimodal Transformer for Multimodal Sequential Learning
The complex world around us is inherently multimodal and sequential (con...
read it

The Garden of Forking Paths: Towards MultiFuture Trajectory Prediction
This paper studies the problem of predicting the distribution over multi...
read it

OptimizationGuided Binary Diversification to Mislead Neural Networks for Malware Detection
Motivated by the transformative impact of deep neural networks (DNNs) on...
read it

PersoninWiFi: Finegrained Person Perception using WiFi
Finegrained person perception such as body segmentation and pose estima...
read it

A Deep Factorization of Style and Structure in Fonts
We propose a deep factorization model for typographic analysis that dise...
read it

Behavior Regularized Offline Reinforcement Learning
In reinforcement learning (RL) research, it is common to assume access t...
read it

Show Your Work: Improved Reporting of Experimental Results
Research in natural language processing proceeds, in part, by demonstrat...
read it

Learning the Difference that Makes a Difference with CounterfactuallyAugmented Data
Despite alarm over the reliance of machine learning systems on socalled...
read it

The NonIID Data Quagmire of Decentralized Machine Learning
Many largescale machine learning (ML) applications need to train ML mod...
read it

Explosive Proofs of Mathematical Truths
Mathematical proofs are both paradigms of certainty and some of the most...
read it

Photosequencing of Motion Blur using Short and Long Exposures
Photosequencing aims to transform a motion blurred image to a sequence o...
read it

SingleNetwork WholeBody Pose Estimation
We present the first singlenetwork approach for 2D wholebody pose esti...
read it

Detecting Patterns of Physiological Response to Hemodynamic Stress via Unsupervised Deep Learning
Monitoring physiological responses to hemodynamic stress can help in det...
read it

GeometryAware Gradient Algorithms for Neural Architecture Search
Many recent stateoftheart methods for neural architecture search (NAS...
read it

TarMAC: Targeted MultiAgent Communication
We explore a collaborative multiagent reinforcement learning setting wh...
read it

Online Model Distillation for Efficient Video Inference
Highquality computer vision models typically address the problem of und...
read it

URFUNNY: A Multimodal Language Dataset for Understanding Humor
Humor is a unique and creative communicative behavior displayed during s...
read it

A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text
When trained effectively, the Variational Autoencoder (VAE) is both a po...
read it

Adversary A3C for Robust Reinforcement Learning
Asynchronous Advantage Actor Critic (A3C) is an effective Reinforcement ...
read it

A Recommendation and Risk Classification System for Connecting Rough Sleepers to Essential Outreach Services
Rough sleeping is a chronic problem faced by some of the most disadvanta...
read it

Regularizing Blackbox Models for Improved Interpretability
Most work on interpretability in machine learning has focused on designi...
read it

MAME : ModelAgnostic MetaExploration
MetaReinforcement learning approaches aim to develop learning procedure...
read it

Deep Multivariate Mixture of Gaussians for Object Detection under Occlusion
In this paper, we consider the problem of detecting object under occlusi...
read it

Estimating 3D Camera Pose from 2D Pedestrian Trajectories
We consider the task of recalibrating the 3D pose of a static surveilla...
read it

Learning from Positive and Unlabeled Data by Identifying the Annotation Process
In binary classification, Learning from Positive and Unlabeled data (LeP...
read it

Minimizing FLOPs to Learn Efficient Sparse Representations
Deep representation learning has become one of the most widely adopted a...
read it

MultiImport: Inferring Node Importance in a Knowledge Graph from Multiple Input Signals
Given multiple input signals, how can we infer node importance in a know...
read it

Universal Inference Using the Split Likelihood Ratio Test
We propose a general method for constructing hypothesis tests and confid...
read it

TransMoMo: InvarianceDriven Unsupervised Video Motion Retargeting
We present a lightweight video motion retargeting approach TransMoMo tha...
read it

Towards Better Interpretability in Deep QNetworks
Deep reinforcement learning techniques have demonstrated superior perfor...
read it

The Laplacian in RL: Learning Representations with Efficient Approximations
The smallest eigenvectors of the graph Laplacian are wellknown to provi...
read it

Adaptive Semantic Segmentation with a Strategic Curriculum of Proxy Labels
Training deep networks for semantic segmentation requires annotation of ...
read it

Robustness of Conditional GANs to Noisy Labels
We study the problem of learning conditional generators from noisy label...
read it

Learning OnRoad Visual Control for SelfDriving Vehicles with Auxiliary Tasks
A safe and robust onroad navigation system is a crucial component of ac...
read it

How Sensitive are SensitivityBased Explanations?
We propose a simple objective evaluation measure for explanations of a c...
read it

ProBO: a Framework for Using Probabilistic Programming in Bayesian Optimization
Optimizing an expensivetoquery function is a common task in science an...
read it
Carnegie Mellon University
943583 Carnegie Mellon University is a private nonprofit research university based in Pittsburgh, Pennsylvania.