52. PointcontrastCode for paper <PointContrast: Unsupervised Pretraining for 3D Point Cloud Understanding>
53. SingSymbol-to-Instrument Neural Generator
54. AgemOfficial implementation of the Averaged Gradient Episodic Memory (A-GEM) in Tensorflow
58. MinirtsWe release dataset collected for our research, code that implement neural network models described in the paper, and scripts to reproduce all of our results, and visualization tool for visualize dataset.
59. Eftvisualization code for 3D human body annotation by EFT (Exemplar Fine-tuning)
60. ContactposeLarge dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images.
61. NbrefCodebase for paper "N-Bref A High-fidelity Decompiler Exploiting Programming Structures"
62. MldocA Corpus for Multilingual Document Classification in Eight Languages.
64. MmbtSupervised Multimodal Bitransformers for Classifying Images and Text
65. CovidprognosisCOVID deterioration prediction based on chest X-ray radiographs via MoCo-trained image representations
66. SentevalA python tool for evaluating the quality of sentence embeddings.
67. PyclsCodebase for Image Classification Research, written in PyTorch.
69. EnormEqui-normalization of Neural Networks
70. Mvfst RlAn asynchronous RL platform for congestion control in QUIC transport protocol. https://arxiv.org/abs/1910.04054.
73. HypernymysuiteHearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora
76. Hanabi spartaResearch code implementing the search AI agent for Hanabi, as well as a web server so people can play against it
77. Nonrigid nerfOpen source repository for the code accompanying the paper 'Non-Rigid Neural Radiance Fields Reconstruction and Novel View Synthesis of a Deforming Scene from Monocular Video'.
78. Poincare EmbeddingsPyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"
79. PosewarperLearning Temporal Pose Estimation from Sparsely Labeled Videos
80. Unbiased TeacherPyTorch code for ICLR 2021 paper Unbiased Teacher for Semi-Supervised Object Detection
81. HvvrHierarchical Visibility for Virtual Reality, which implements a hybrid CPU/GPU ray-caster, suited for real time rendering of effects such as lens distortion.
82. TalkthewalkThis repository provides code for reproducing experiments of the paper Talk The Walk: Navigating New York City Through Grounded Dialogue by Harm de Vries, Kurt Shuster, Dhruv Batra, Devi Parikh, Jason Weston, and Douwe Kiela.
85. MultipathnetA Torch implementation of the object detection network from "A MultiPath Network for Object Detection" (https://arxiv.org/abs/1604.02135)
86. SimmcWith the aim of building next generation virtual assistants that can handle multimodal inputs and perform multimodal actions, we introduce two new datasets (both in the virtual shopping domain), the annotation schema, the core technical tasks, and the baseline models. The code for the baselines and the datasets will be opensourced.
87. Graph2nncode for paper "Graph Structure of Neural Networks"
88. Commai EnvA platform for developing AI systems as described in A Roadmap towards Machine Intelligence - http://arxiv.org/abs/1511.08130
89. Differentiable Robot ModelWe are implementing differentiable models of robot manipulators, which allows us to learn typically assumed to be known models of robots for control and motion planning. These models can then be used in more complex reinforcement learning settings, hopefully making learning more sample-efficient. Furthermore, such differentiable models can also be used for learning simulators.
90. Fbtt EmbeddingThis is a Tensor Train based compression library to compress sparse embedding tables used in large-scale machine learning models such as recommendation and natural language processing. We showed this library can reduce the total model size by up to 100x in Facebook’s open sourced DLRM model while achieving same model quality. Our implementation is faster than the state-of-the-art implementations. Existing the state-of-the-art library also decompresses the whole embedding tables on the fly therefore they do not provide memory reduction during runtime of the training. Our library decompresses only the requested rows therefore can provide 10,000 times memory footprint reduction per embedding table. The library also includes a software cache to store a portion of the entries in the table in decompressed format for faster lookup and process.
91. VisslVISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.
93. Sound SpacesA first-of-its-kind acoustic simulation platform for audio-visual embodied AI research. It supports training and evaluating multiple tasks and applications.
95. SlboAlgorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees
96. CollaqA code implementation for our arXiv paper "Multi-agent Adhoc Team Play using Decompositional Q function"
100. QhoptimImplementations of quasi-hyperbolic optimization algorithms.