Research-Methods

This repository contains papers and other resources for the Research Methods class

New papers

Reinforcement Learning Papers

1. Playing Atari with Deep Reinforcement Learning, Algorithm: DQN.
2. Asynchronous Methods for Deep Reinforcement Learning
3. Grandmaster level in StarCraft II using multi-agent reinforcement learning
4. The Ingredients of Real World Robotic Reinforcement Learning
5. Concrete Problems in AI Safety
6. Deep Reinforcement Learning that matters
7. Benchmarking Reinforcement Learning Algorithms on Real-World Robots
8. Dueling Network Architectures for Deep Reinforcement Learning
9. DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
10. Deep reinforcement learning from human preferences
11. Strategic Attentive Writer for Learning Macro-Actions
12. Prioritized Experience Replay
13. Learning to Paint With Model-based Deep Reinforcement Learning
14. A Review of Cooperative Multi-Agent Deep Reinforcement Learning
15. Machine Learning for Combinatorial Optimization: a Methodological Tour d’Horizon
16. Deep Reinforcement Learning for Autonomous Driving: A Survey
17. Resource Management with Deep Reinforcement Learning
18. Deep Reinforcement Learning with Double Q-learning
19. Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
20. Language Models are Few-Shot Learners
21. Towards a Human-like Open-Domain ChatbotNeural Combinatorial Optimization with Reinforcement Learning
22. Multi-Agent Reinforcement Learning for Dynamic Routing Games: A Unified Paradigm
23. Deep Reinforcement Learning for Cyber Security
24. Learning Combinatorial Optimization Algorithms over Graphs
25. Challenges of Real-World Reinforcement Learning
26. Deep reinforcement learning for time series: playing idealized trading games*
27. Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving
28. Unsupervised Doodling and Painting with Improved SPIRAL
29. Dream to Control: Learning Behaviors by Latent Imagination
30. Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
31. Proximal Policy Optimization Algorithms
32. Deterministic Policy Gradient Algorithms
33. QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
34. Solving Rubik's Cube with a Robot Hand
35. A Hybrid of Deep Reinforcement Learning and Local Search for the Vehicle Routing Problems
36. Continuous control with deep reinforcement learning
37. Variational Intrinsic Control
38. FeUdal Networks for Hierarchical Reinforcement Learning
39. Learning Dexterous In-Hand Manipulation
40. The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning

NLP Papers

5. Effective approaches to attention-based neural machine translation
6. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer 10.Neural Approaches to Conversational AI
7. ALBERT: A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS
8. Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
9. Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
10. Listen, attend and spell: A neural network for large vocabulary conversational speech recognition
11. Restricted Boltzmann Machines for Collaborative Filtering
12. Language Models are Few-Shot Learners
13. Towards a Human-like Open-Domain Chatbot
14. Analysis Methods in Neural Language Processing: A Survey
15. Jukebox: A Generative Model for Music
16. RoBERTa: A Robustly Optimized BERT Pretraining Approach
17. XLNet: Generalized Autoregressive Pretraining for Language Understanding
18. StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding

CV papers

1. Gated Graph Sequence Neural Networks
2. Graph attention networks
3. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
4. Pay attention to MLPs
5. DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
6. Visualizing and Understanding Convolutional Networks
7. Face Detection with a 3D Model
8. Taming Transformers for High-Resolution Image Synthesis
9. Deep learning-enabled medical computer vision
10. Densely Connected Convolutional Networks
11. Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art
12. Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning
13. Spherical CNNs
14. Adversarial Examples that Fool both Computer Vision and Time-Limited Humans
15. A Closed-form Solution to Photorealistic Image Stylization
16. Adam: A Method for Stochastic Optimization
17. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
18. Deep Learning using Rectified Linear Units (ReLU)
19. Deep Learning in Label-free Cell Classification
20. Generative Pretraining from Pixels
21. Deep Learning for Deepfakes Creation and Detection: A Survey
22. Very deep convolutional networks for large-scale image recognition
23. Anycost GANs for Interactive Image Synthesis and Editing
24. Deep-Anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenes
25. Zero-Shot Text-to-Image Generation
26. Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
27. Learning Transferable Visual Models From Natural Language Supervision
28. Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks

Past Papers

NLP

1. Attention is all you need
2. Deep Learning for Hate Speech Detection in Tweets
3. Deep content-based music recommendation
4. Sequence to sequence model 12.Emotion-Cause Pair Extraction: A New Task To Emotion Analysis In Texts 11.A Neural Conversational Model
5. Neural machine translation by jointly learning to align and translate
6. High Fidelity Speech Synthesis with Adversarial Networks
7. WinoGrande: An Adversarial Winograd Schema Challenge at Scale
8. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
9. Onsets and Frames: Dual-Objective Piano Transcription
10. Reformer: The Efficient Transformer
11. Animating Pictures with Eulerian Motion Fields
12. Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews
13. Convolutional sequence to sequence learning

CV

2. ImageNet Classification with Deep Convolutional Neural Networks
3. Deep Residual Learning for Image Recognition
4. You Only Look Once: Unified, Real-Time Object Detection
5. Old Photo Restoration via Deep Latent Space Translation
6. Generative Adversarial Networks
7. Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation