paper-notes

This contains my notes of research papers I've read during the time working on my undergraduate thesis, with topics ranging from deep learning, reinforcement learning, computer vision, and cognitive science. Papers are organized chronologically by publication date, and then further arranged by topic. The paper titles here are linked to my notes (those without links are in progress). Inspired by Daniel Seita

2019

• BabyAI: First Steps Towards Grounded Language Learning With a Human In the Loop, ICLR 2019, [Paper]
• Time-Agnostic Prediction: Predicting Predictable Video Frames, ICLR 2019, [Paper]
• M^3RL: Mind-aware Multi-agent Management Reinforcement Learning, ICLR 2019, [Paper]
• Eidetic 3D LSTM: A Model for Video Prediction and Beyond, ICLR 2019, [Paper]
• Analogues of Mental Simulation and Imagination in Deep Learning, Current Opinion in Behavioral Sciences 2019, [Paper]
• The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision, ICLR 2019, [Paper]
• Reasoning About Physical Interactions with Object-Oriented Prediction and Planning, ICLR 2019, [Paper]
• Learning Unsupervised Learning Rules, ICLR 2019 Oral, [Paper]

2018

• 3D-Aware Scene Manipulation via Inverse Graphics, NeurIPS 2018 [Paper]
• Neural Scene Representation and Rendering, Science 2018 [Page]
• Learning Shape Priors for Single-View 3D Completion and Reconstruction, ECCV 2018 [Paper]
• Neural Processes, [Paper]
• Encoding Spatial Relations from Natural Language, [Paper]
• Learning Models for Visual 3D Localization with Implicit Mapping, [Paper]
• Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding, NeurIPS 2018 [Paper]
• Machine Theory of Mind, PMLR 2018 [Page]
• Investigating Human Priors for Playing Video Games, ICML 2018 [Paper]
• Learning to Play With Intrinsically-Motivated, Self-Aware Agents [Paper]
• Visual Curiosity: Learning to Ask Questions to Learn Visual Recognition, CoRL 2018 Oral [Paper]
• Exploration by Random Network Distillation [Paper]
• Are GANs Created Equal? A Large-Scale Study, NeurIPS 2018 [Paper]
• Stochastic Video Generation with a Learned Prior, PMLR 2018 [Paper]
• Stochastic Variational Video Prediction, ICLR 2018 [Paper]
• Learning Hierarchical Semantic Image Manipulation through Structured Representations, NeurIPS 2018 [Paper]
• Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Active Tasks, [Page]
• Deep Curiosity Search: Intra-Life Exploration Can Improve Performance on Challenging Deep Reinforcement Learning Problems, NeurIPS 2018 [Paper]
• An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents Felipe, [Paper]
• Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm, ICLR 2018 [Paper]
• Emergent Complexity via Multi-Agent Competition, ICLR 2018 [Paper]

2017

• Learning to See Physics via Visual De-animation, NeurIPS 2017 Spotlight [Page]
• A Compositional Object-Based Approach to Learning Physical Dynamics, ICLR 2017, [Page]
• MarrNet: 3D Shape Reconstruction via 2.5D Sketches, NeurIPS 2017 [Paper]
• Building machines that learn and think like people, Behavioral and Brain Sciences 2017 [Paper]
• Curiosity-driven Exploration by Self-supervised Prediction, ICML 2017 [Page]
• PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs, NeurIPS 2017 [Paper]
• Multi-agent Reinforcement Learning in Sequential Social Dilemmas, [Paper]
• Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments, NeurIPS 2017 [Paper]
• Learning with Opponent-Learning Awareness, [Paper]

2016

• Single Image 3d Interpreter Network, ECCV 2016 [Paper]
• Generating Videos with Scene Dynamics, NeurIPS 2016 [Paper]
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling, NeurIPS 2016 [Paper]
• Visual Dynamics: Stochastic Future Generation via Layered Cross Convolutional Networks, NeurIPS 2016 [Page]
• Anticipating Visual Representations from Unlabeled Video, CVPR 2016 [Paper]
• View Synthesis by Appearance Flow, ECCV 2016 [Paper]
• Towards Conceptual Compression, NeurIPS 2016 [Paper]
• Opponent Modeling in Deep Reinforcement Learning, PMLR 2016 [Page]
• Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation, NeurIPS 2016 [Paper]

2015

• Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning, NeurIPS 2015 [Paper]
• Learning Visual Biases from Human Imagination, NeurIPS 2015 [Paper]
• A Recurrent Latent Variable Model for Sequential Data, NeurIPS 2015 [Paper]
• DRAW: A Recurrent Neural Network For Image Generation, PMLR 2015 [Paper]

2014

• Learning physics from dynamical scenes, CogSci 2014 [Paper]

2013

• Simulation as an Engine to Physical Scene Understanding, PNAS 2013, [Paper]
• Harvesting Motion Patterns from Still Images from the Internet, CogSci 2014 Oral, [Paper]

Before 2013

• Formal Theory of Creativity, Fun, and Intrinsic Motivation, [Paper]
• Intrinsically Motivated Reinforcement Learning, [Paper]
• Where Do Rewards Come From?, [Paper]