
Towards transformationresilient provenance detection of digital media
Advancements in deep generative models have made it possible to synthesi...
read it

Training Generative Adversarial Networks by Solving Ordinary Differential Equations
The instability of Generative Adversarial Network (GAN) training has fre...
read it

Enabling certification of verificationagnostic networks via memoryefficient semidefinite programming
Convex relaxations have emerged as a promising approach for verifying de...
read it

Uncovering the Limits of Adversarial Training against NormBounded Adversarial Examples
Adversarial training and its variants have become de facto standards for...
read it

Contrastive Training for Improved OutofDistribution Detection
Reliable detection of outofdistribution (OOD) inputs is increasingly u...
read it

Evaluating the Apperception Engine
The Apperception Engine is an unsupervised learning system. Given a sequ...
read it

Strong Generalization and Efficiency in Neural Programs
We study the problem of learning efficient algorithms that strongly gene...
read it

Lagrangian Decomposition for Neural Network Verification
A fundamental component of neural network verification is the computatio...
read it

Achieving Robustness in the Wild via Adversarial Mixing with Disentangled Representations
Recent research has made the surprising finding that stateoftheart de...
read it

Reducing Sentiment Bias in Language Models via Counterfactual Evaluation
Recent improvements in largescale language models have driven progress ...
read it

Learning Transferable Graph Exploration
This paper considers the problem of efficient exploration of unseen envi...
read it

An Alternative Surrogate Loss for PGDbased Adversarial Testing
Adversarial testing methods based on Projected Gradient Descent (PGD) ar...
read it

Making sense of sensory input
This paper attempts to answer a central question in unsupervised learnin...
read it

CLEVRER: CoLlision Events for Video REpresentation and Reasoning
The ability to reason about temporal and causal events from videos lies ...
read it

Branch and Bound for Piecewise Linear Neural Network Verification
The success of Deep Learning and its potential use in many safetycritic...
read it

Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation
Neural networks are part of many contemporary NLP systems, yet their emp...
read it

Adversarial Robustness through Local Linearization
Adversarial training is an effective methodology for training deep neura...
read it

Are Labels Required for Improving Adversarial Robustness?
Recent work has uncovered the interesting (and somewhat surprising) find...
read it

A Hierarchical Probabilistic UNet for Modeling MultiScale Ambiguities
Medical imaging only indirectly measures the molecular identity of the t...
read it

REGAL: Transfer Learning For Fast Optimization of Computation Graphs
We present a deep reinforcement learning approach to optimizing the exec...
read it

Graph Matching Networks for Learning the Similarity of Graph Structured Objects
This paper addresses the challenging problem of retrieval and matching o...
read it

Knowing When to Stop: Evaluation and Verification of Conformity to Outputsize Specifications
Models such as SequencetoSequence and ImagetoSequence are widely use...
read it

The NeuroSymbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
We propose the NeuroSymbolic Concept Learner (NSCL), a model that lear...
read it

Structured agents for physical construction
Physical construction  the ability to compose objects, subject to phys...
read it

Analysing Mathematical Reasoning Abilities of Neural Models
Mathematical reasoninga core ability within human intelligencepres...
read it

MetaLearning surrogate models for sequential decision making
Metalearning methods leverage past experience to learn datadriven indu...
read it

Degenerate Feedback Loops in Recommender Systems
Machine learning is used extensively in recommender systems deployed in ...
read it

Verification of NonLinear Specifications for Neural Networks
Prior work on neural network verification has focused on specifications ...
read it

Scaling shared model governance via model splitting
Currently the only techniques for sharing governance of a deep learning ...
read it

Verification of deep probabilistic models
Probabilistic models are a critical part of the modern deep learning too...
read it

Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures
This paper addresses the problem of evaluating learning systems in safet...
read it

Compositional Imitation Learning: Explaining and executing one task at a time
We introduce a framework for Compositional Imitation Learning and Execut...
read it

Strength in Numbers: Tradingoff Robustness and Computation via AdversariallyTrained Ensembles
While deep learning has led to remarkable results on a number of challen...
read it

On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models
Recent works have shown that it is possible to train models that are ver...
read it

NeuralSymbolic VQA: Disentangling Reasoning from Vision and Language Understanding
We marry two powerful ideas: deep representation learning for visual rec...
read it

Learning to Follow Language Instructions with Adversarial Reward Induction
Recent work has shown that deep reinforcementlearning agents can learn ...
read it

Relational inductive biases, deep learning, and graph networks
Artificial intelligence (AI) has undergone a renaissance recently, makin...
read it

Value Propagation Networks
We present Value Propagation (VProp), a parameterefficient differentiab...
read it

Training verified learners with learned verifiers
This paper proposes a new algorithmic framework,predictorverifier train...
read it

Efficient Relaxations for Dense CRFs with Sparse Higher Order Potentials
Dense conditional random fields (CRFs) with Gaussian pairwise potentials...
read it

Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis
Program synthesis is the task of automatically generating a program cons...
read it

Programmatically Interpretable Reinforcement Learning
We study the problem of generating interpretable and verifiable policies...
read it

A Dual Approach to Scalable Verification of Deep Networks
This paper addresses the problem of formally verifying desirable propert...
read it

Can Neural Networks Understand Logical Entailment?
We introduce a new dataset of logical entailments for the purpose of mea...
read it

Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
This paper investigates recently proposed approaches for defending again...
read it

Piecewise Linear Neural Network verification: A comparative study
The success of Deep Learning and its potential use in many important saf...
read it

Semantic Code Repair using NeuroSymbolic Transformation Networks
We study the problem of semantic code repair, which can be broadly defin...
read it

Neural Program MetaInduction
Most recently proposed methods for Neural Program Induction work under t...
read it

ZeroShot Task Generalization with MultiTask Deep Reinforcement Learning
As a step towards developing zeroshot task generalization capabilities ...
read it

Ensemble Bayesian Optimization
Bayesian Optimization (BO) has been shown to be a very effective paradig...
read it