Object-Oriented Learning (OOL): Perception, Representation, and Reasoning

International Conference on Machine Learning (ICML)

Friday July 17, 2020, Virtual Workshop

Access the virtual workshop page


For each paper being presented at the workshop, we will host (1) pre-recorded content (either from SlidesLive or via YouTube), (2) a Rocket.Chat chatroom for text-based discussion and (3) a Zoom meeting room. All of these can be found from each paper's landing page (which you can access by clicking on the title of the relevant paper).

The Zoom meeting rooms will be open only during the poster session timeslots (see the Schedule), during which authors will join the meeting rooms to allow you to ask them questions face-to-face. We encourage you to first watch the presentation associated with the paper, and then join the Zoom meeting room to ask questions and engage in further discussion.

Session 1 (3:30-4:30pm UTC)

Title Authors PDF
Learning Affordances in Object-Centric Generative Models (Oral) Yizhe Wu, Sudhanshu Kasewa, Oliver M Groth, Sasha Salter, Li Sun, Oiwi Parker Jones, and Ingmar Posner PDF
Conditional Set Generation with Transformers (Spotlight) Adam R Kosiorek, Hyunjik Kim, and Danilo Jimenez Rezende PDF
Unsupervised Object Keypoint Learning using Local Spatial Predictability (Spotlight) Anand Gopalakrishnan, Sjoerd van Steenkiste, and Jürgen Schmidhuber PDF
Generative Adversarial Set Transformers (Spotlight) Karl Stelzner, Kristian Kersting, and Adam R Kosiorek PDF
Capsule Networks: A Generative Probabilistic Perspective (Spotlight) Lewis SG Smith, Lisa Schut, Yarin Gal, and Mark van der Wilk PDF
Learning Object-Centric Representations for High-Level Planning in Minecraft (Spotlight) Steven D James, Benjamin Rosman, and George Konidaris PDF
Amodal 3D Reconstruction for Robotic Manipulation via Stability and Connectivity (Spotlight) William Agnew, Christopher Xie, Aaron T Walsman, Octavian V Murad, Yubo Wang, Pedro Domingos, and Siddhartha Srinivasa PDF
Hierarchical Relational Inference Aleksandar Stanic, Sjoerd van Steenkiste, and Jürgen Schmidhuber PDF
Unsupervised Learning of Independently Controllable Dynamic Components Andrii Zadaianchuk and Georg Martius PDF
SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Design Ari Seff, Yaniv Ovadia, Wenda Zhou, and Ryan P Adams PDF
Generative Graph Perturbations for Scene Graph Prediction Boris Knyazev, Harm De Vries, Cătălina Cangea, Graham Taylor, Aaron Courville, and Eugene Belilovsky PDF
Systematically Comparing Neural Network Architectures in Relation Leaning Guy Davidson and Brenden M Lake PDF
Reconstruction Bottlenecks in Object-Centric Generative Models Martin Engelcke, Oiwi Parker Jones, and Ingmar Posner PDF
Structured Generative Modeling of Images with Object Depths and Locations Titas Anciukevičius, Christoph H Lampert, and Paul Henderson PDF

Session 2 (11:00-11:59pm UTC)

Title Authors PDF
Learning 3D Object-Oriented World Models from Unlabeled Videos (Oral) Eric Crawford and Joelle Pineau PDF
Counterfactual Data Augmentation using Locally Factored Dynamics (Oral) Silviu Pitis, Elliot Creager, and Animesh Garg PDF
Hierarchical Decomposition and Generation of Scenes with Compositional Objects (Spotlight) Fei Deng, Zhuo Zhi, and Sungjin Ahn PDF
Rapid policy updating in human physical construction (Spotlight) William P McCarthy and Judy Fan PDF
Slot Contrastive Networks: A Contrastive Approach for Representing Objects Evan Racah and Sarath Chandar PDF
Library learning for structured object concepts Haoliang Wang and Judy Fan PDF
iSprites: A Dataset for Identifiable Multi-Object Representation Learning Jack Brady and Geoffrey Roeder PDF
Geometry-Aware Modeling of Rigid Body Physics Kexin Yi, Toru Lin, and Phillip Isola PDF
Representation Learning Through Latent Canonicalizations Or Litany, Ari Morcos, Srinath Sridhar, Leonidas Guibas, and Judy Hoffman PDF
Better Set Representations For Relational Reasoning Qian Huang, Horace He, Abhay Singh, Yan Zhang, Ser-Nam Lim, and Austin R Benson PDF
Time for a Background Check! Uncovering the Influence of Background Features on Deep Neural Networks Vikash Sehwag, Rajvardhan Oak, Mung Chiang, and Prateek Mittal PDF
ROMA: A Relational Object Modeling Agent for Sample-Efficient Reinforcement Learning Wilka Carvalho, Anthony Liang, Kimin Lee, Sungryull Sohn, Honglak Lee, Richard L Lewis, and Satinder Singh PDF
Generating Stochastic Object Dynamics in Scenes Zhixuan Lin, Yi-Fu Wu, Skand Skand, Bofeng Fu, Jindong Jiang, and Sungjin Ahn PDF