- Amsterdam
- http://tkipf.github.io
Stars
Code release for ICLR 2023 paper: SlotFormer on object-centric dynamics models
Your self-hosted, globally interconnected microblogging community
Library for the training and evaluation of object-centric models (ICML 2022)
Toolbox for molecular animations in Blender, powered by Geometry Nodes.
Website
Code for the paper: Putting An End to End-to-End: Gradient-Isolated Learning of Representations
Implementation of Slot Attention from GoogleAI
This is official Pytorch implementation of "Graph Refinement based Airway Extraction using Mean-Field Networks and Graph Neural Networks", Raghavendra Selvan et al. 2020
Flax is a neural network library for JAX that is designed for flexibility.
The entmax mapping and its loss, a family of sparse softmax alternatives.
Python code to generate the Toulouse Road Network dataset introduced in "Image-Conditioned Graph Generation for Road Network Extraction"
PyTorch implementation of "Image-Conditioned Graph Generation for Road Network Extraction"
PHYRE is a benchmark for physical reasoning.
Turn Python scripts into handouts with Markdown and figures
Code for the paper Physics-as-Inverse-Graphics: Joint Unsupervised Learning of Objects and Physics from Video
Template for building 2D grid worlds with OpenAI Gym and Pycolab
Adapting the AlphaZero algorithm to remove the need of execution traces to train NPI.
Learning and Reasoning with Graph-Structured Data (ICML 2019 Workshop)
Reproduction work of "Neural Relational Inference for Interacting Systems" in Chainer
Hyperparameter optimization that enables researchers to experiment, visualize, and scale quickly.
Approximating Wasserstein distances with PyTorch
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
official implementation for the paper "Simplifying Graph Convolutional Networks"
Code for the paper "Language Models are Unsupervised Multitask Learners"
Graph Neural Networks with Keras and Tensorflow 2.