Papers-2018.md

December 2018

• Improving the Interpretability of Deep Neural Networks with Knowledge Distillation - [Arxiv] [QA]
• Adaptive Confidence Smoothing for Generalized Zero-Shot Learning - [Arxiv] [QA]
• Grounded Human-Object Interaction Hotspots from Video - [Arxiv] [QA]
• Abstracting Causal Models - [Arxiv] [QA]
• Face Completion with Semantic Knowledge and Collaborative Adversarial Learning - [Arxiv] [QA]
• Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders - [Arxiv] [QA]
• Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning - [Arxiv] [QA]
• Deep Inception Generative Network for Cognitive Image Inpainting - [Arxiv] [QA]

November 2018

• Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects - [Arxiv] [QA]
• Coordinate-based Texture Inpainting for Pose-Guided Image Generation - [Arxiv] [QA]
• GAN Dissection: Visualizing and Understanding Generative Adversarial Networks - [Arxiv] [QA]
• Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles - [Arxiv] [QA]
• Bytes are All You Need: End-to-End Multilingual Speech Recognition and Synthesis with Bytes - [Arxiv] [QA]
• Causal Inference by String Diagram Surgery - [Arxiv] [QA]
• Transferable Interactiveness Knowledge for Human-Object Interaction Detection - [Arxiv] [QA]
• Generalized Zero-Shot Recognition based on Visually Semantic Embedding - [Arxiv] [QA]
• Scalable agent alignment via reward modeling: a research direction - [Arxiv] [QA]
• On Hallucinating Context and Background Pixels from a Face Mask using Multi-scale GANs - [Arxiv] [QA]
• Grasp2Vec: Learning Object Representations from Self-Supervised Grasping - [Arxiv] [QA]
• Reward learning from human preferences and demonstrations in Atari - [Arxiv] [QA]
• CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling - [Arxiv] [QA]
• Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning - [Arxiv] [QA]
• Generative Dual Adversarial Network for Generalized Zero-shot Learning - [Arxiv] [QA]
• Blockwise Parallel Decoding for Deep Autoregressive Models - [Arxiv] [QA]
• Image Chat: Engaging Grounded Conversations - [Arxiv] [QA]
• Persistent-Homology-based Machine Learning and its Applications -- A Survey - [Arxiv] [QA]

October 2018

• Taking Human out of Learning Applications: A Survey on Automated Machine Learning - [Arxiv] [QA]
• Automatically Evolving CNN Architectures Based on Blocks - [Arxiv] [QA]
• Image Inpainting via Generative Multi-column Convolutional Neural Networks - [Arxiv] [QA]
• Graph HyperNetworks for Neural Architecture Search - [Arxiv] [QA]
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding - [Arxiv] [QA]
• Batch Active Preference-Based Learning of Reward Functions - [Arxiv] [QA]
• Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning - [Arxiv] [QA]

September 2018

• Learning Long-Range Perception Using Self-Supervision from Short-Range Sensors and Odometry - [Arxiv] [QA]
• TVQA: Localized, Compositional Video Question Answering - [Arxiv] [QA]

August 2018

• AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale - [Arxiv] [QA]
• iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection - [Arxiv] [QA]
• Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning - [Arxiv] [QA]
• All You Need is "Love": Evading Hate-speech Detection - [Arxiv] [QA]
• Learning Human-Object Interactions by Graph Parsing Neural Networks - [Arxiv] [QA]
• Everybody Dance Now - [Arxiv] [QA]
• Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction - [Arxiv] [QA]
• Self-Supervised Model Adaptation for Multimodal Semantic Segmentation - [Arxiv] [QA]
• Learning Actionable Representations from Visual Observations - [Arxiv] [QA]
• Efficient Progressive Neural Architecture Search - [Arxiv] [QA]

July 2018

• Regional Multi-scale Approach for Visually Pleasing Explanations of Deep Neural Networks - [Arxiv] [QA]
• Improving Spatiotemporal Self-Supervision by Deep Reinforcement Learning - [Arxiv] [QA]
• Diverse feature visualizations reveal invariances in early layers of deep neural networks - [Arxiv] [QA]
• Cross-lingual Argumentation Mining: Machine Translation (and a bit of Projection) is All You Need! - [Arxiv] [QA]
• Explaining Image Classifiers by Counterfactual Generation - [Arxiv] [QA]
• TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time - [Arxiv] [QA]
• Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search - [Arxiv] [QA]
• Visual Reinforcement Learning with Imagined Goals - [Arxiv] [QA]
• Representation Learning with Contrastive Predictive Coding - [Arxiv] [QA]
• Talk the Walk: Navigating New York City through Grounded Dialogue - [Arxiv] [QA]
• A Tutorial on Bayesian Optimization - [Arxiv] [QA]
• Seq2RDF: An end-to-end application for deriving Triples from Natural Language Text - [Arxiv] [QA]

June 2018

• A Benchmark for Interpretability Methods in Deep Neural Networks - [Arxiv] [QA]
• This Looks Like That: Deep Learning for Interpretable Image Recognition - [Arxiv] [QA]
• Video Inpainting by Jointly Learning Temporal Structure and Spatial Details - [Arxiv] [QA]
• RISE: Randomized Input Sampling for Explanation of Black-box Models - [Arxiv] [QA]
• Self-Supervised Feature Learning by Learning to Spot Artifacts - [Arxiv] [QA]
• Polynomial Regression As an Alternative to Neural Nets - [Arxiv] [QA]
• Resource-Efficient Neural Architect - [Arxiv] [QA]
• Auto-Meta: Automated Gradient Based Meta Learner Search - [Arxiv] [QA]
• Free-Form Image Inpainting with Gated Convolution - [Arxiv] [QA]
• Dank Learning: Generating Memes Using Deep Neural Networks - [Arxiv] [QA]
• A Peek Into the Hidden Layers of a Convolutional Neural Network Through a Factorization Lens - [Arxiv] [QA]
• Soccer on Your Tabletop - [Arxiv] [QA]

May 2018

• Explaining Explanations: An Overview of Interpretability of Machine Learning - [Arxiv] [QA]
• How Important Is a Neuron? - [Arxiv] [QA]
• Rethinking Knowledge Graph Propagation for Zero-Shot Learning - [Arxiv] [QA]
• Theory and Experiments on Vector Quantized Autoencoders - [Arxiv] [QA]
• AutoAugment: Learning Augmentation Policies from Data - [Arxiv] [QA]
• Semantic Network Interpretation - [Arxiv] [QA]
• Controlling Personality-Based Stylistic Variation with Neural Natural Language Generators - [Arxiv] [QA]
• Progressive Ensemble Networks for Zero-Shot Recognition - [Arxiv] [QA]
• Unsupervised Learning of Neural Networks to Explain Neural Networks - [Arxiv] [QA]
• DVAE#: Discrete Variational Autoencoders with Relaxed Boltzmann Priors - [Arxiv] [QA]
• A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations - [Arxiv] [QA]
• Fighting Fake News: Image Splice Detection via Learned Self-Consistency - [Arxiv] [QA]
• SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting - [Arxiv] [QA]
• Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination - [Arxiv] [QA]
• AGI Safety Literature Review - [Arxiv] [QA]
• Learnable PINs: Cross-Modal Embeddings for Person Identity - [Arxiv] [QA]

April 2018

• How convolutional neural network see the world - A survey of convolutional neural network visualization methods - [Arxiv] [QA]
• FaceShop: Deep Sketch-based Face Image Editing - [Arxiv] [QA]
• Subgoal Discovery for Hierarchical Dialogue Policy Learning - [Arxiv] [QA]
• Image Inpainting for Irregular Holes Using Partial Convolutions - [Arxiv] [QA]
• Audio-Visual Scene Analysis with Self-Supervised Multisensory Features - [Arxiv] [QA]
• Bimonoidal Structure of Probability Monads - [Arxiv] [QA]
• Deep Painterly Harmonization - [Arxiv] [QA]
• The Sound of Pixels - [Arxiv] [QA]
• Learning to Separate Object Sounds by Watching Unlabeled Video - [Arxiv] [QA]
• Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspection - [Arxiv] [QA]
• The simple essence of automatic differentiation - [Arxiv] [QA]

March 2018

• Meta-Learning Update Rules for Unsupervised Representation Learning - [Arxiv] [QA]
• MemGEN: Memory is All You Need - [Arxiv] [QA]
• Structural inpainting - [Arxiv] [QA]
• Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning - [Arxiv] [QA]
• BAGAN: Data Augmentation with Balancing GAN - [Arxiv] [QA]
• Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs - [Arxiv] [QA]
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge - [Arxiv] [QA]
• Preserving Semantic Relations for Zero-Shot Learning - [Arxiv] [QA]

February 2018

• Relational Reasoning for Markov Chains in a Probabilistic Guarded Lambda Calculus - [Arxiv] [QA]
• Machine Theory of Mind - [Arxiv] [QA]
• Machine Theory of Mind - [Arxiv] [QA]
• Diversity is All You Need: Learning Skills without a Reward Function - [Arxiv] [QA]
• Multimodal Explanations: Justifying Decisions and Pointing to the Evidence - [Arxiv] [QA]
• DVAE++: Discrete Variational Autoencoders with Overlapping Transformations - [Arxiv] [QA]
• On Characterizing the Capacity of Neural Networks using Algebraic Topology - [Arxiv] [QA]
• A Survey Of Methods For Explaining Black Box Models - [Arxiv] [QA]
• Learning Image Representations by Completing Damaged Jigsaw Puzzles - [Arxiv] [QA]
• The Matrix Calculus You Need For Deep Learning - [Arxiv] [QA]
• Singularities in Einstein-conformally coupled Higgs cosmological models - [Arxiv] [QA]
• Interpreting CNNs via Decision Trees - [Arxiv] [QA]

January 2018

• Shift-Net: Image Inpainting via Deep Feature Rearrangement - [Arxiv] [QA]
• Understanding Deep Architectures by Visual Summaries - [Arxiv] [QA]
• Generative Image Inpainting with Contextual Attention - [Arxiv] [QA]
• Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networks - [Arxiv] [QA]