On the Relation Between Unit Testing and Code Quality

Unit testing has been considered as having a key role in building highquality software, and therefore it has been widely used in practice. However,data on the relationship between unit testing... | Continue reading


@arxiv.org | 41 minutes ago

XLNet: Generalized Autoregressive Pretraining for Language Understanding

With the capability of modeling bidirectional contexts, denoisingautoencoding based pretraining like BERT achieves better performance thanpretraining approaches based on autoregressive language... | Continue reading


@arxiv.org | 7 hours ago

“Can I Implement Your Algorithm?” Model for Reproducible Research Software(2014)

The reproduction and replication of novel results has become a major issuefor a number of scientific disciplines. In computer science and relatedcomputational disciplines such as systems... | Continue reading


@arxiv.org | 9 hours ago

Learning Execution through Neural Code Fusion

As the performance of computer systems stagnates due to the end of Moore'sLaw, there is a need for new models that can understand and optimize theexecution of general purpose code. While there... | Continue reading


@arxiv.org | 13 hours ago

Inferred successor maps for better transfer learning

Humans and animals show remarkable flexibility in adjusting their behaviourwhen their goals, or rewards in the environment change. While such flexibilityis a hallmark of intelligent behaviour,... | Continue reading


@arxiv.org | 17 hours ago

Subsumption-driven clause learning with DPLL+restarts

We propose to use a DPLL+restart to solve SAT instances by successivesimplifications based on the production of clauses that subsume the initialclauses. We show that this approach allows the... | Continue reading


@arxiv.org | 17 hours ago

Learning to Plan Hierarchically from Curriculum

We present a framework for learning to plan hierarchically in domains withunknown dynamics. We enhance planning performance by exploiting problemstructure in several ways: (i) We simplify the... | Continue reading


@arxiv.org | 17 hours ago

Approximate Normalization for Gradual Dependent Types

Dependent types help programmers write highly reliable code. However, thisreliability comes at a cost: it can be challenging to write new prototypes in(or migrate old code to) dependently-typed... | Continue reading


@arxiv.org | 1 day ago

HotStuff: BFT Consensus in the Lens of Blockchain

We present HotStuff, a leader-based Byzantine fault-tolerant replicationprotocol for the partially synchronous model. Once network communicationbecomes synchronous, HotStuff enables a correct... | Continue reading


@arxiv.org | 1 day ago

Event2Mind: Commonsense Inference on Events, Intents, and Reactions

We investigate a new commonsense inference task: given an event described ina short free-form text ("X drinks coffee in the morning"), a system reasonsabout the likely intents ("X wants to stay... | Continue reading


@arxiv.org | 1 day ago

“My Way of Telling a Story”: Persona Based Grounded Story Generation

Visual storytelling is the task of generating stories based on a sequence ofimages. Inspired by the recent works in neural generation focusing oncontrolling the form of text, this paper explores... | Continue reading


@arxiv.org | 1 day ago

Effects Without Monads: Non-Determinism Back to the Meta Language

We reflect on programming with complicated effects, recalling anundeservingly forgotten alternative to monadic programming and checking to seehow well it can actually work in modern functional... | Continue reading


@arxiv.org | 2 days ago

Pe2D Convolutional Neural Networks for Sequence-to-Sequence Prediction

Current state-of-the-art machine translation systems are based onencoder-decoder architectures, that first encode the input sequence, and thengenerate an output sequence based on the input... | Continue reading


@arxiv.org | 2 days ago

Effective problem solving using SAT solvers

In this article we demonstrate how to solve a variety of problems and puzzlesusing the built-in SAT solver of the computer algebra system Maple. Once theproblems have been encoded into Boolean... | Continue reading


@arxiv.org | 2 days ago

Recurrent Neural Processes

We extend Neural Processes (NPs) to sequential data through Recurrent NPs orRNPs, a family of conditional state space models. RNPs can learn dynamicalpatterns from sequential data and deal with... | Continue reading


@arxiv.org | 2 days ago

SQIL: Imitation Learning via Regularized Behavioral Cloning

Learning to imitate expert behavior given action demonstrations containinghigh-dimensional, continuous observations and unknown dynamics is a difficultproblem in robotic control. Simple... | Continue reading


@arxiv.org | 2 days ago

Adversarial Training Can Hurt Generalization

While adversarial training can improve robust accuracy (against anadversary), it sometimes hurts standard accuracy (when there is no adversary).Previous work has studied this tradeoff between... | Continue reading


@arxiv.org | 2 days ago

Turing complete mechanical processor via automated nonlinear system design

Nanomechanical computers promise a greatly improved energetic efficiencycompared to their electrical counterparts. However, progress towards this goalis hindered by a lack of modular components,... | Continue reading


@arxiv.org | 3 days ago

An Overview of Memristive Cryptography

Smaller, smarter and faster edge devices in the Internet of things erademands secure data analysis and transmission under resource constraints ofhardware architecture. Lightweight cryptography... | Continue reading


@arxiv.org | 3 days ago

A recipe for irreproducible results (2017)

Recent studies have shown that many results published in peer-reviewedscientific journals are not reproducible. This raises the following question:why is it so easy to fool myself into believing... | Continue reading


@arxiv.org | 3 days ago

Neural Arabic Question Answering

This paper tackles the problem of open domain factual Arabic questionanswering (QA) using Wikipedia as our knowledge source. This constrains theanswer of any question to be a span of text in... | Continue reading


@arxiv.org | 3 days ago

Compositional generalization through meta sequence-to-sequence learning

People can learn a new concept and use it compositionally, understanding howto "blicket twice" after learning how to "blicket." In contrast, powerfulsequence-to-sequence (seq2seq) neural... | Continue reading


@arxiv.org | 3 days ago

Comet: Commonsense Transformers for Automatic Knowledge Graph Construction

We present the first comprehensive study on automatic knowledge baseconstruction for two prevalent commonsense knowledge graphs: ATOMIC (Sap etal., 2019) and ConceptNet (Speer et al., 2017).... | Continue reading


@arxiv.org | 3 days ago

Three Other Models of Computer System Performance (2018)

This note argues for more use of simple models beyond Amdahl's Law:Bottleneck Analysis, Little's Law, and a M/M/1 Queue. | Continue reading


@arxiv.org | 4 days ago

Show HN: Fakta – Automated End-to-End Fact Checking with Deep Learning

We present FAKTA which is a unified framework that integrates variouscomponents of a fact checking process: document retrieval from media sourceswith various types of reliability, stance... | Continue reading


@arxiv.org | 4 days ago

There is no general AI: Why Turing machines cannot pass the Turing test

Since 1950, when Alan Turing proposed what has since come to be called theTuring test, the ability of a machine to pass this test has established itselfas the primary hallmark of general AI. To... | Continue reading


@arxiv.org | 4 days ago

KCAT: A Knowledge-Constraint Typing Annotation Tool

Fine-grained Entity Typing is a tough task which suffers from noise samplesextracted from distant supervision. Thousands of manually annotated samples canachieve greater performance than... | Continue reading


@arxiv.org | 4 days ago

Better Character Language Modeling Through Morphology

We incorporate morphological supervision into character language models(CLMs) via multitasking and show that this addition improves bits-per-character(BPC) performance across 24 languages, even... | Continue reading


@arxiv.org | 4 days ago

Cognitive Model Priors for Predicting Human Decisions

Human decision-making underlies all economic behavior. For the past fourdecades, human decision-making under uncertainty has continued to be explainedby theoretical models based on prospect... | Continue reading


@arxiv.org | 4 days ago

Temporal Type Theory: A topos-theoretic approach to systems and behavior (2017)

This book introduces a temporal type theory, the first of its kind as far aswe know. It is based on a standard core, and as such it can be formalized in aproof assistant such as Coq or Lean by... | Continue reading


@arxiv.org | 5 days ago

Antlia2's role in driving the ripples in the outer gas disk of the Galaxy

We employ the observed Gaia proper motions of the newly discovered Antlia 2dwarf galaxy to calculate its orbital distribution in the cosmologically recentpast. Using these observationally... | Continue reading


@arxiv.org | 5 days ago

Search for Non-Standard Parity Violation Sources in Jets at S√=8 TeV W CMS Data

The Standard Model violates parity, but only by mechanisms which areinvisible to Large Hadron Collider (LHC) experiments (on account of the lack ofinitial state polarisation or spin-sensitivity... | Continue reading


@arxiv.org | 5 days ago

SPoC: Search-Based Pseudocode to Code

We consider the task of mapping pseudocode to long programs that arefunctionally correct. Given test cases as a mechanism to validate programs, wesearch over the space of possible translations... | Continue reading


@arxiv.org | 6 days ago

Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)

Sarcasm is often expressed through several verbal and non-verbal cues, e.g.,a change of tone, overemphasis in a word, a drawn-out syllable, or a straightlooking face. Most of the recent work in... | Continue reading


@arxiv.org | 6 days ago

Tackling Climate Change with Machine Learning

Climate change is one of the greatest challenges facing humanity, and we, asmachine learning experts, may wonder how we can help. Here we describe howmachine learning can be a powerful tool in... | Continue reading


@arxiv.org | 6 days ago

The Assumptions of Frauchiger and Renner

This note is a critical examination of the argument of Frauchiger and Renner(Nature Communications 9:3711 (2018)), in which they claim to show that threereasonable assumptions about the use of... | Continue reading


@arxiv.org | 6 days ago

Provably Robust Deep Learning

Recent works have shown the effectiveness of randomized smoothing as ascalable technique for building neural network-based classifiers that areprovably robust to $\ell_2$-norm adversarial... | Continue reading


@arxiv.org | 6 days ago

Task-Aware Deep Sampling for Feature Generation

The human ability to imagine the variety of appearances of novel objectsbased on past experience is crucial for quickly learning novel visual conceptsbased on few examples. Endowing machines... | Continue reading


@arxiv.org | 6 days ago

New Schmidhuber Paper on Minimax Games

Generative Adversarial Networks (GANs) learn to model data distributionsthrough two unsupervised neural networks, each minimizing the objectivefunction maximized by the other. We relate this... | Continue reading


@arxiv.org | 7 days ago

Generating Diverse High-Fidelity Images with VQ-VAE-2

We explore the use of Vector Quantized Variational AutoEncoder (VQ-VAE)models for large scale image generation. To this end, we scale and enhance theautoregressive priors used in VQ-VAE to... | Continue reading


@arxiv.org | 7 days ago

What Does Bert Look At? An Analysis of BERT's Attention

Large pre-trained neural networks such as BERT have had great recent successin NLP, motivating a growing body of research investigating what aspects oflanguage they are able to learn from... | Continue reading


@arxiv.org | 7 days ago

Learning Powerful Policies by Using Consistent Dynamics Model

Model-based Reinforcement Learning approaches have the promise of beingsample efficient. Much of the progress in learning dynamics models in RL hasbeen made by learning models via supervised... | Continue reading


@arxiv.org | 7 days ago

Detecting Dark Matter with Aharonov-Bohm

While the evidence for dark matter continues to grow, the nature of the darkmatter remains a mystery. A dark $U(1)_D$ gauge theory can have a small kineticmixing with the visible photon which... | Continue reading


@arxiv.org | 8 days ago

Physics of Suction Cups

We have developed a theory for the contact between suction cups and randomlyrough surfaces. The theory predicts the dependency of the pull-off time(lifetime) on the pull-off force, and is tested... | Continue reading


@arxiv.org | 8 days ago

Watch, Try, Learn: Meta-Learning from Demonstrations and Reward

Imitation learning allows agents to learn complex behaviors fromdemonstrations. However, learning a complex vision-based task may require animpractical number of demonstrations. Meta-imitation... | Continue reading


@arxiv.org | 8 days ago

Learning Individual Styles of Conversational Gesture

Human speech is often accompanied by hand and arm gestures. Given audiospeech input, we generate plausible gestures to go along with the sound.Specifically, we perform cross-modal translation... | Continue reading


@arxiv.org | 8 days ago

Datalog Disassembly

Disassembly is fundamental to binary analysis and rewriting. We present anovel disassembly technique that takes a stripped binary and producesreassembleable assembly code. The resulting assembly... | Continue reading


@arxiv.org | 8 days ago

Energy and Policy Considerations for Deep Learning in NLP [pdf]

Recent progress in hardware and methodology for training neural networks hasushered in a new generation of large networks trained on abundant data. Thesemodels have obtained notable gains in... | Continue reading


@arxiv.org | 9 days ago