NVlabs / Bongard-LOGO
Bongard-LOGO is a Python code repository with the purpose of generating synthetic Bongard problems on a large scale with little human intervention.
☆51Updated 2 years ago
Alternatives and similar repositories for Bongard-LOGO:
Users that are interested in Bongard-LOGO are comparing it to the libraries listed below
- PyTorch implementation for The Scattering Compositional Learner (SCL)☆32Updated 4 years ago
- Measuring compositionality in representation learning☆73Updated 5 years ago
- PyTorch implementation of paper "Visual Concept-Metaconcept Learner", NeruIPS 2019☆48Updated 5 years ago
- Official Release of NeurIPS 2020 Spotlight paper "Generative Neurosymbolic Machines"☆35Updated last year
- PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World [ACL 2021]☆54Updated 3 years ago
- Learning with latent language☆50Updated 3 years ago
- This framework provides out-of-the-box implementations of Referential Games variants in order to study the emergence of artificial langua…☆22Updated last week
- EfficientMORL (ICML'21)☆22Updated 3 years ago
- Python implementation of Bayesian Program Learning tools (with PyTorch)☆71Updated 2 years ago
- Systematic generalization test for CLEVR☆15Updated 5 years ago
- An implementation of the MONet model for unsupervised scene decomposition in PyTorch☆58Updated 2 years ago
- Solving reinforcement learning tasks which require language and vision☆32Updated last year
- Learning Perceptual Inference by Contrasting☆27Updated 2 years ago
- Grounded SCAN data set.☆69Updated 3 years ago
- Self-supervised learning through the eyes of a child☆140Updated 3 years ago
- Library for the training and evaluation of object-centric models (ICML 2022)☆68Updated last year
- Neural Networks that convert input movies into Physical Scene Graphs (PSGs)☆62Updated 4 years ago
- Usable implementation of Emerging Symbol Binding Network (ESBN), in Pytorch☆24Updated 4 years ago
- An implementation of 2021 paper by Geoffrey Hinton: "How to represent part-whole hierarchies in a neural network" in Pytorch.☆58Updated 3 years ago
- Make quick mechanical turk HTML/Javascript interfaces and launch them with Python functions☆41Updated 3 years ago
- Burgess et al. "MONet: Unsupervised Scene Decomposition and Representation"☆88Updated 2 years ago
- Starter Kit for the NeurIPS 2019 Disentanglement Challenge☆33Updated 2 years ago
- Code, data and benchmark from the paper "Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences".☆36Updated 3 years ago
- "CoPhy: Counterfactual Learning of Physical Dynamics", F. Baradel, N. Neverova, J. Mille, G. Mori, C. Wolf, ICLR'2020☆33Updated 4 years ago
- CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning☆104Updated 4 years ago
- Experiments for Meta-Learning Symmetries by Reparameterization☆56Updated 3 years ago
- Attribute-Object Visual Composition using Attributes as Operators☆65Updated 2 years ago
- A Pytorch implementation of "Measuring abstract reasoning in neural networks" in ICML 2018 by DeepMind☆37Updated last year
- Neural-Grammar-Symbolic Learning with Back-Search☆52Updated 8 months ago
- Official PyTorch implementation of "Improving Generative Imagination in Object-Centric World Models"☆35Updated 2 years ago