How To Read Research Papers

Controlled abstention neural networks for identifying skillful predictions for classification problems. (arXiv:2104.08281v1 [physics.ao-ph])
The earth system is exceedingly complex and often chaotic in nature, making prediction incredibly challenging: we cannot expect to make...

Better Latent Spaces for Better Autoencoders. (arXiv:2104.08291v1 [hep-ph])
Autoencoders as tools behind anomaly searches at the LHC have the structural problem that they only work in one direction,...

Learning to Reason for Text Generation from Scientific Tables. (arXiv:2104.08296v1 [cs.CL])
In this paper, we introduce SciGen, a new challenge dataset for the task of reasoning-aware data-to-text generation consisting of tables...

Text2App: A Framework for Creating Android Apps from Text Descriptions. (arXiv:2104.08301v1 [cs.CL])
We present Text2App -- a framework that allows users to create functional Android applications from natural language specifications. The conventional...

Capturing Row and Column Semantics in Transformer Based Question Answering over Tables. (arXiv:2104.08303v1 [cs.AI])
Transformer based architectures are recently used for the task of answering questions over tables. In order to improve the accuracy...

Membership Inference Attack Susceptibility of Clinical Language Models. (arXiv:2104.08305v1 [cs.CL])
Deep Neural Network (DNN) models have been shown to have high empirical privacy leakages. Clinical language models (CLMs) trained on...

Neural Transfer Learning for Repairing Security Vulnerabilities in C Code. (arXiv:2104.08308v1 [cs.SE])
In this paper, we address the problem of automatic repair of software vulnerabilities with deep learning. The major problem with...

An implementation of an efficient direct Fourier transform of polygonal areas and volumes. (arXiv:2104.08309v1 [math.NA])
Calculations of the Fourier transform of a constant quantity over an area or volume defined by polygons (connected vertices) are...

Learning to Boost the Efficiency of Modern Code Review. (arXiv:2104.08310v1 [cs.SE])
Modern Code Review (MCR) is a standard in all kinds of organizations that develop software. MCR pays for itself through...

Data Shapley Valuation for Efficient Batch Active Learning. (arXiv:2104.08312v1 [stat.ML])
Annotating the right set of data amongst all available data points is a key challenge in many machine learning applications....

Does language help generalization in vision models?. (arXiv:2104.08313v1 [cs.AI])
Vision models trained on multimodal datasets have recently proved very efficient, both in terms of the wide availability of large...

High Performance Convolution Using Sparsity and Patterns for Inference in Deep Convolutional Neural Networks. (arXiv:2104.08314v1 [cs.CV])
Deploying deep Convolutional Neural Networks (CNNs) is impacted by their memory footprint and speed requirements, which mainly come from convolution....

Surface Form Competition: Why the Highest Probability Answer Isn't Always Right. (arXiv:2104.08315v1 [cs.CL])
Large language models have shown promising results in zero-shot settings (Brown et al.,2020; Radford et al., 2019). For example, they...

Li$_x$CoO$_2$ phase stability studied by machine learning-enabled scale bridging between electronic structure, statistical mechanics and phase field theories. (arXiv:2104.08318v1 [cond-mat.mtrl-sci])
Li$_xTM$O$_2$ (TM={Ni, Co, Mn}) are promising cathodes for Li-ion batteries, whose electrochemical cycling performance is strongly governed by crystal structure...

Multitask Learning for VVC Quality Enhancement and Super-Resolution. (arXiv:2104.08319v1 [cs.CV])
The latest video coding standard, called versatile video coding (VVC), includes several novel and refined coding tools at different levels...

Bayesian Active Learning with Pretrained Language Models. (arXiv:2104.08320v1 [cs.CL])
Active Learning (AL) is a method to iteratively select data for annotation from a pool of unlabeled data, aiming to...

libEnsemble: A Library to Coordinate the Concurrent Evaluation of Dynamic Ensembles of Calculations. (arXiv:2104.08322v1 [cs.DC])
Almost all applications stop scaling at some point; those that don't are seldom performant when considering time to solution on...

Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators. (arXiv:2104.08323v1 [cs.LG])
Deep neural network (DNN) accelerators received considerable attention in recent years due to the potential to save energy compared to...

On the Robustness to Misspecification of $\alpha$-Posteriors and Their Variational Approximations. (arXiv:2104.08324v1 [stat.ML])
$\alpha$-posteriors and their variational approximations distort standard posterior inference by downweighting the likelihood and introducing variational approximation errors. We show...

CTU Depth Decision Algorithms for HEVC: A Survey. (arXiv:2104.08328v1 [cs.MM])
High-Efficiency Video Coding (HEVC) surpasses its predecessors in encoding efficiency by introducing new coding tools at the cost of an...


Source: RSS news feeds for arXiv updates