Studies
Clarifying what I studied
2019
- Story Ending Generation with Incremental Encoding and Commonsense Knowledge
- Text Generation from Knowledge Graphs with Graph Transformers
- COMET: Commonsense Transformers for Automatic Knowledge Graph Construction
- GQA: A New Dataset for Real-World Visual Reasoning ans compositional Question Answering
- Generative Question Answering: Learning to Answer the Whole Question
- Visual Question Generation as Dual Task of Visual Question Answering
- Task-Oriented Query Reformulation with Reinforcement Learning
- Learning to Reason: End-to-End Module Networks for Visual Question Answering
- Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge
- Large-Scale Answerer in Questioner's Mind for Visual Dialog Question Generation
- Answerer in Questioner's Mind: Information Theoretic Approach to Goal-Oriented Visual Dialog
- Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
- Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
- Compositional Attention Networks for Machine Reasoning
- Hierarchical Question-Image Co-Attention for Visual Question Answering
- MUTAN: Multimodal Tucker Fusion for Visual Question Answering
- Chain of Reasoning for Visual Question Answering
- Deformable Convolutional Networks
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- MobileNet: Efficient Convolutional Neural Networks for Mobile Vision Applications
- StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
- U-net: Convolutional Networks for Biomedical Image Segmentation
- A Style-Based Generator Architecture for Generative Adversarial Networks
- Neural Arithmetic Logit Units
- VAE with a VampPrior
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Bilinear Attention Networks
- Hybrid computing using a neural network with dynamic external memory
- SSD: Single Shot MultiBox Detector
- Progressive Growing of GANs for improved Quality, Stability, and Variation
- BERT: Pretraining of Deep Bidirectional Transformers for Language Understanding
2018
- On the Dimensionality of Word Embedding
- Inferring and Executing Programs for Visual Reasoning
- Deep Compositional Question Answering with Neural Module Networks
- Tracking Emerges by Colorizing Videos
- Latent Alignment and Variational Attention
- FiLM: Visual Reasoning with a General Conditioning Layer
- TasNet: Time-Domain Audio Separation Network for Real-Time Single-channel Speech Separation
- Recurrent Relational Networks
- Modularity Matters: Learning Invariant Relational Reasoning Tasks
- Learning Visual Question Answering by Bootstrapping Hard Attention
- Relational Deep Reinforcement Learning
- Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding
- Learning to Reconstruct Shapes from Unseen Classes
- Isolating Sources of Disentanglement in VAEs
- Relationships from Entity Stream
- Linguistic Regularities in Sparse and Explicit Word Representations
- Linguistic Regularities in Continuous Space Word Representations
- Scalable Distributed DNN Training Using Commodity GPU Cloud Computing
- Neural Word Embedding as Implicit Matrix Factorization
- Dependency-Based Word Embeddings
- Large Scale Distributed Deep Networks
- Improving Distributional Similarity with Lessons Learned from Wrod Embeddings
- Hadamard Product for Low-rank Bilinear Pooling
- Stacked Attention Networks for Image Question Answering
- Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing
- The Hadoop Distributed File System
- Multimodal Residual Learning for Visual QA
- REEF: Retainable Evaluator Execution Framework
- Apache Hadoop YARN: Yet Another Resource Negotiator
- MapReduce: Simplified Data Processing on Large Clusters
- Mesos: A Platform for Fine-Grained Resource Sharing in the Data Center
- Relational Recurrent Neural Network
- Phase-aware Speech Enhancement with Deep Complex U-net
- Transformation Autoregressive Networks
- Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
- Neural Process
- Grammar Variational Autoencoder
- IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis
- Deep AutoRegressive Networks
- Deep Generative Image Models using a Laplacian Pyramid of Adversarial Network
- Breaking the Softmax Bottleneck: A High-Rank RNN Language Model
- Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond
- Variational Inference for Monte Carlo Objectives
- Noisy Network for Exploration
- Unsupervised Deep Embedding for Clustering Analysis
- Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
- Spectral Normalization for Generative Adversarial Networks
- A Two-Step Disentanglement Method
- Deep Contextualized Word Representations
- Neural Variational Inference and Learning in Belief Networks
- Neural Autoregressive Distribution Estimation
- Glow: Generative Flow with Invertible 1x1 Convolutions
- A Character-Level Decoder without Explicit Segmentation for Neural Machine Translation
- Density Estimation Using Real NVP
- NICE: Non-linear Independent Components Estimation
- Categorical Reparameterization with Gunbel-Softmax
- Deterministic Policy Gradient Algorithms
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- How Does Batch Normalization Help Optimization? (No, It Is Not About Internal Covariate Shift
- World Models
- Gradient Estimation Using Stochastic Computation Graphs
- Amortized Inference in Probabilistic Reasoning
- Distributed Prioritized Experience Replay
- A Hierarchical Latent Variable Encoder-Decoder model for Generating Dialogues
- Forward-Backward Reinforcement Learning
- A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning
- RUDDER: Return Decomposition for Delayed Rewards
- Fixing a Broken ELBO
- Understanding deep learning requires rethinking generalization
- Learning to See by Moving
- Adversarial Variational Bayes: Unifying Variational Autoencoder and Generative Adversarial Networks
- Massively Parallel Methods for Deep Reinforcement Learning
- Spatial Transformer Networks
- Learning Disentangled Representations with Semi-Supervised Deep Generative Models
- Neural Turing Machine
- Hierarchical Variational Autoencoders for Music
- Highway Network
- Importance Weighted Autoencoders
- Deep Recurrent Q-Learning for Partially Observable MDPs
- An Efficient Framework for Learning Sentence Representations
- A Deep Generative Model for Disentangled Representations of Sequential Data
- DRAW: A Recurrent Neural Nerwork For Image Generation
- Disentangling Controllable and Uncontrollable Factors of Variation by Interacting with the World
- Learning Hierarchical Features from Generative models
- Curriculum Learning
- Ladder Variational Autoencoders
- Independently Controlable Factors
- The Consciousness Prior
- Matching Networks for One Shot Learning
- Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks
- Generating Sentences from a Continuous Space
- SCAN: Learning Hierarchical Compositional Visual Concepts
- A simple neural network module for relational reasoning
- Understanding Disentangling in Beta-VAE
- Deep Variational Information Bottleneck
- Deep Convolutional Inverse Graphics Network
- Semi-supervised Learning with Deep Generative Models
- Variational Inference of Disentangled Latent Concepts from Unlabeled Observations
- Disentangling by Factorising
- Adversarially Regularized Autoencoders
- Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data
- Multimodal Unsupervised Image-to-Image Translation
- PixelGAN Autoencoders
- Conditional Image Synthesis with Auxiliary Classifier GANs
- Disentangling Factors of Variation in Deep Representations Using Adversarial Training
- Variational Lossy Autoencoders
- Adversarial Autoencoders
- Parallel WaveNet: Fast High-Fidelity Speech Synthesis
- Unpaired Image-to-image Translation using Cycle-Consistent Adversarial Network
- Improved Variational Inference with Inverse Autoregressive Flow
- Masked Autoregressive Flow for Density Estimation
- MADE: Masked Autoencoder for Distribution Estimation
- Variational Inference with Normalizing Flows
- Continuous Control with Deep Reinforcement Learning
- PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications
- Model-Free Episodic Control
- Neural Discrete Representation Learning
- Wavenet: A Generative Model For Raw Audio
- Pixel Recurrent Neural Networks
- Attention is all you need
- Prioritized Experience Replay
- Dueling Network Architectures for Deep Reinforcement Learning
- Deep Reinforcement Learning with Double Q-learning
- Wasserstein Auto-Encoders
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- Wasserstein GAN
- Bi-Directional Attention Flow for Machine Comprehension
- SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
- Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
- Dynamic Routing Between Capsules
- Memory Networks
- Mask R-CNN
- Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
- Ask the Right Questions: Active Question Reformulation with Reinforcement Learning
- Auto-Encoder Variational Bayes
- Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
- Early Visual Concept Learning with Unsupervised Deep Learning
- Human-level control through deep reinforcement learning
- Neural Machine Translation by Jointly Learning to Align and Translate
- Dynamic Topic Model
- GloVe: Global Vectors for Word Representation
- node2vec
- Distributed Representations of Words and Phrases and their Compositionality
- Distributed Representations of Sentences and Documents
- Efficient Estimation of Word Representations in Vector Space
