# Reading List

## Generic


**---Important---**
- (Jindong) 2007.Causal Discovery in Physical Systems from Videos
Expressive power of graph neural networks and the Weisfeiler-Lehman test
- (Sungjin) 1911.High Fidelity Video Prediction with Large Stochastic Recurrent Nerual Networks
- (Sungjin) 2006.Object Files and Schemata - Factorizing Declarative and Procedural Knowledge in Dynamical Systems
- (Sungjin) 2006.Compositional Video Synthesis with Action Graphs

**---Carried-Over---**
- 2006.Rapid Task-Solving in Novel Environments
- (Yi-Fu) 2006.Denoising Diffusion Probabilistic Models
- (Chang) 1804.Neural Kinematic Networks for Unsupervised Motion Retargetting
- 2002.Cutting out the Middle-Man- Training and Evaluating Energy-Based Models without Sampling
- 2004.TraDE- Transformers for Density Estimation
- (Fei) 2006.Kinematic Structure - Preserved Representation for Unsupervised 3D Human Pose Estimation

**--- Contrastive Loss & Self-Supervised Learning---**
- (Junghyun) 1905.Data-efficient image recognition with contrastive predictive

**--- Causality ---**
- 1904.DAG-GNN - DAG Structure Learning with Graph Neural Networks
- Gradient-Based Neural DAG Learning With Interventions
- 2006.Deep Structural Causal Models for Tractable Counterfactual Inference

**--- WOOL ---**
- (Bofeng) Learning Affordances in Object-Centric Generative Models
- (Sungjin) 2006.Unsupervised Object Keypoint Learning using Local Spatial Predictability
- (Sungjin) 2006.Structured Generative Modeling of Images with Object Depths and Locations
- (Jindong) 2006.Better Set Repreentations For Relational Reasoning
- (Jaesik) Video Prediction with Temporal Hierarchies
- Library Learning for Structured Object Concepts
- (Jindong) 2006.Geometry-Aware Modeling of Rigid Body Physics
- (Yi-Fu) Slot Contrastive Networks: A Contrastive Approach for Representing Objects
- (Fei) Conditional Set Generation with Transformers

## Done
- (Gautam) 2006.Hierarchical Relational Inference
- (Yi-Fu) 2006.Generative Pretraining from Pixels
- (Fei) Gradient Estimation with Stochastic Softmax Tricks
- (Gautam) 2006.Discovering Symbolic Models from Deep Learning with Inductive Biases
- (Fei) Pointer Graph Networks
- (Jaesik) 2006.Implicit Neural Represnetations with Periodic Activation Functions
- (Yi-Fu) Prototypical Contrastive Learning of Unsupervised Representations
- (Victor) Learning Compositional Rules via Neural Program Synthesis
- (Bofeng) 1904.Attention augmented convolutional networks
- (Junghyun) Bootstrap Your Own Latent A New Approach to Self-Supervised Learning
- (Chang) Joint Training of Variational Auto-Encoder and Latent Energy-Based Model
- (Skand) Big Self-Supervised Models are Strong Semi-Supervised Learners
- (Fei) BSP-Net: Generating Compact Meshes via Binary Space Partitioning
- (Yi-Fu) Grounding Language in Play
- (Skand) Planning to Explore via Self-Supervised World Models
- (Chang) PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
- (Jindong) Probing Emergent Semantics in Predictive Agents via Question Answering
- (Junghyun) A Simple Framework for Contrastive Learning of Visual Representations (SimCLR)

### Need-more-time papers
- 2006.DreamCoder - Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning
- 2006.Is Independence all you need? On the Generalization of Representations Learned from Correlated Data
- Einsum Networks- Fast and Scalable Learning of Tractable Probabilistic Circuits
- Optimizing agent behavior over long time scales by transporting value
- What Makes for Good Views for Contrastive Learning?
- A theory of independent mechanisms for extrapolation in generative models
- 2006.Counterfactual Data Augmentation using Locally Factored Dynamics

### TODO
2002.Weakly-Supervised Disentanglement Without Compromises
2006.What can I do here? A Theory of Affordances in Reinforcement Learning
2006.Compositional Explanations of Neurous
20xx.Compositional generalization by factorizing alignment and translation
2006.Improving Generative Imagination in Object-Centric World Models
2006.Transformers are RNNs - Fast Autoregressive Transformers with Linear Attention
2006.Causality and Batch Reinforcement Learning - Complementary Approaches To Planning In Unknown Domains
2006.A causal view of compositional zero-shot recognition
2006.Object-Centric Learning with Slot Attention
2007.Robustifying Sequential Neural Processes
2006.Amortized Causal Discovery - Learning to Infer Causal Graphs from Time-Series Data
2006.Disentangling by Subspace Diffusion
2006.Riemannian Continuous Normalizing Flows
2006.SE(3)-Transormers - 3D Roto-Translation Equivariant Attention Networks
2006.Learning Causal Models Online
2006.A survey on graph kernels
2006.Set Distribution Networks - a Generative Model for Sets of Images
2006.Geometric Prediction-Moving Beyond Scalars
2006.Equivariant Neural Rendering