facebookresearch/SlowFast: PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

facebookresearch/deepmask: Torch implementation of DeepMask and SharpMask

facebookresearch/GCSAL: Global Climate Statistical Analysis Library (GCSAL) allows viewing of climate statistics formulated from over 60 years of data acquisition at 3000 locations around the world.

facebookresearch/EmbodiedQA: Train embodied agents that can answer questions in environments

facebookresearch/TextVQA: Website for TextVQA dataset.

facebookresearch/impact-driven-exploration: impact-driven-exploration

facebookresearch/BLINK: Entity Linker solution

facebookresearch/active-mri-acquisition: Active Acquisition for fastMRI

facebookresearch/diplomacy_searchbot: Code to accompany "Human-Level Performance in No-Press Diplomacy via Equilibrium Search", published at ICLR 2021

facebookresearch/xR-EgoPose: New egocentric synthetic dataset for egocentric 3D human pose estimation

facebookresearch/NSVF: Open source code for the paper of Neural Sparse Voxel Fields.

facebookresearch/moolib: A library for distributed ML training with PyTorch

facebookresearch/uimnet: What classifiers know what they don't know?

facebookresearch/aroma-paper-artifacts: Paper Artifacts for "Aroma: Code Recommendation via Structural Code Search"

facebookresearch/phosa: Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild

facebookresearch/covid19_spread: Modeling the spread of COVID-19

facebookresearch/c3dm: Code for Canonical 3D Deformable Mapping (C3DM) paper

facebookresearch/2.5D-Visual-Sound: 2.5D visual sound

facebookresearch/low-shot-with-diffusion: Low-shot learning with large-scale diffusion

facebookresearch/alebo: Re-Examining Linear Embeddings for High-dimensional Bayesian Optimization

facebookresearch/ELF: An End-To-End, Lightweight and Flexible Platform for Game Research

facebookresearch/icp-block-mdp: Invariant Causal Prediction for Block MDPs

facebookresearch/gan_of_gan: stylegan project

facebookresearch/WyPR: Code release for CVPR 2021 paper "3D Spatial Recognition without Spatially Labeled 3D"

facebookresearch/clevr-iep: Inferring and Executing Programs for Visual Reasoning

facebookresearch/SparseConvNet: Submanifold sparse convolutional networks

facebookresearch/asset: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations

facebookresearch/xcit: Official code Cross-Covariance Image Transformer (XCiT)

facebookresearch/UNLU: Code for the paper "UnNatural Language Inference" to appear at ACL 2021 (Long Paper)

facebookresearch/droidlet: A modular embodied agent architecture and platform for building embodied agents

facebookresearch/ContextualBO: Code associated with paper "High-Dimensional Contextual Policy Search with Unknown Context Rewards using Bayesian Optimization"

facebookresearch/CollaQ: A code implementation for our arXiv paper "Multi-agent Adhoc Team Play using Decompositional Q function"

facebookresearch/SimulEval: SimulEval: A General Evaluation Toolkit for Simultaneous Translation

facebookresearch/binary-image-selection: BISON: Binary Image SelectiON

facebookresearch/multiset-compression: Official code accompanying the arXiv paper Compressing Multisets with Large Alphabets

facebookresearch/fairmotion: Tools to load, process and visualize motion capture data

facebookresearch/EgoCom-Dataset: EgoCom: A Multi-person Multi-modal Egocentric Communications Dataset

facebookresearch/ConvNeXt: Code release for ConvNeXt model

facebookresearch/Detic: Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".

facebookresearch/torchrec: Pytorch domain library for recommendation systems

facebookresearch/av_hubert: A self-supervised learning framework for audio-visual speech

facebookresearch/barlowtwins: PyTorch implementation of Barlow Twins.

facebookresearch/domainbed_measures: Code accompanying the paper on "An Empirical Investigation of Domain Generalization with Empirical Risk Minimizers" published at NeurIPS, 2021

facebookresearch/phyre: PHYRE is a benchmark for physical reasoning.

facebookresearch/KILT: Library for Knowledge Intensive Language Tasks

facebookresearch/mae: PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

facebookresearch/tdfbanks: Pytorch implementation of time-domain filterbanks

facebookresearch/interaction-exploration: Code for "Learning Affordance Landscapes for Interaction Exploration in 3D Environments" (NeurIPS 20)

facebookresearch/ContactPose: Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images.

facebookresearch/House3D: a Realistic and Rich 3D Environment

facebookresearch/certified-removal: Certified Removal from Machine Learning Models

facebookresearch/clara: CLARA: Confidence of Labels and Raters

facebookresearch/BinauralSDM: This repository contains a set of tools to render Binaural Room Impulse Responses (BRIR) using the Spatial Decomposition Method (SDM).The implementation features a series of improvements presented in Amengual et al. 2020, such as quantization of the direction of arrival (DOA) estimates to improve the spectral properties of the rendered BRIRs, or RTMod and RTMod+AP equalization for the late reverberation.The repository also contains the necessary files to 3D print an array holder of optimized topology for the estimation of DOA information.

facebookresearch/DeeperCluster: Implements the unsupervised pre-training of convolutional neural networks

facebookresearch/protein-ebm: Energy-based models for atomic-resolution protein conformations

facebookresearch/EmpatheticDialogues: Dialogue model that produces empathetic responses when trained on the EmpatheticDialogues dataset.

facebookresearch/video-long-term-feature-banks: Long-Term Feature Banks for Detailed Video Understanding

facebookresearch/fair_self_supervision_benchmark: Scaling and Benchmarking Self-Supervised Visual Representation Learning

facebookresearch/votenet: Deep Hough Voting for 3D Object Detection in Point Clouds

facebookresearch/pyrobot: PyRobot: An Open Source Robotics Research Platform

facebookresearch/GloRe: Global Reasoning module for visual recognition

facebookresearch/ScaDiver: Project for the paper "A Scalable Approach to Control Diverse Behaviors for Physically Simulated Characters"

facebookresearch/low-shot-shrink-hallucinate: Presenting Low-shot Visual Recognition by Shrinking and Hallucinating Features

facebookresearch/CoDraw: CoDraw dataset

facebookresearch/fairo: A modular embodied agent architecture and platform for building embodied agents

facebookresearch/mmbt: Supervised Multimodal Bitransformers for Classifying Images and Text

facebookresearch/dlrm: An implementation of a deep learning recommendation model (DLRM)

facebookresearch/amortized-optimization-tutorial: Tutorial on amortized optimization for learning to optimize over continuous domains

facebookresearch/craftassist: A virtual assistant bot in Minecraft

facebookresearch/AttentiveNAS: code for "AttentiveNAS Improving Neural Architecture Search via Attentive Sampling"

facebookresearch/AlphaNet: AlphaNet Improved Training of Supernet with Alpha-Divergence

facebookresearch/dynabench: Dynamic Adversarial Benchmarking platform

facebookresearch/VisualEchoes: VisualEchoes Dataset (ECCV 2020)

facebookresearch/grounded-video-description: Video Grounding and Captioning

facebookresearch/Generic-Grouping: Open-source code for Generic Grouping Network (GGN, CVPR 2022)

facebookresearch/rl: A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

facebookresearch/fewshotDatasetDesign: The paper studies the problem of learning to recognize a new class of objects from a very small number of labeled images. This is called few-shot learning. Previous work in the literature focused on designing new algorithms that allow to learn to generalize to new unseen classes.In this work, we consider the impact of the dataset that we train on, and experiment with some dataset manipulations to see which trade-offs are important in the design of a dataset aimed at few-shot learning.

facebookresearch/online_dialog_eval: Code for the paper "Learning an Unreferenced Metric for Online Dialogue Evaluation", ACL 2020

facebookresearch/XLM: PyTorch original implementation of Cross-lingual Language Model Pretraining.

facebookresearch/asym-siam: PyTorch implementation of Asymmetric Siamese (https://arxiv.org/abs/2204.00613)

facebookresearch/ContactOpt: Physical contact plays a critical role in hand and object grasping. By estimating desirable contact then optimizing the hand pose to achieve it, ContactOpt improves the accuracy and realism of estimated hand and object poses.

facebookresearch/aqa-study: This repo contains the data (question/answer pairs and their associated passages from Wikipedia) collected and used in the following paperDivyansh Kaushik, Douwe Kiela, Zachary C. Lipton, Wen-tau Yih. "On the Efficacy of Adversarial Data Collection for Question Answering Results from a Large-Scale Randomized Study." In ACL-2021.

facebookresearch/multigrain: Code for "MultiGrain: a unified image embedding for classes and instances"

facebookresearch/libri-light: dataset for lightly supervised training using the librivox audio book recordings. https://librivox.org/.

facebookresearch/FiD: Fusion-in-Decoder

facebookresearch/SING: Symbol-to-Instrument Neural Generator

facebookresearch/connect-caption-and-trace: A unified framework to jointly model images, text, and human attention traces.

facebookresearch/co3d: Tooling for the Common Objects In 3D dataset.

facebookresearch/MLQA: New dataset

facebookresearch/SentEval: A python tool for evaluating the quality of sentence embeddings.

facebookresearch/SegmPred: Predicting Deeper into the Future of Semantic Segmentation

facebookresearch/deep-variance-reduction: On the Ineffectiveness of Variance Reduced Optimization for Deep Learning

facebookresearch/torch_ucc: Pytorch process group third-party plugin for UCC

facebookresearch/LAMA: LAnguage Model Analysis

facebookresearch/simmc2: Code for SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations

facebookresearch/poincare-embeddings: PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"

facebookresearch/selavi: This repo covers the implementation for Labelling unlabelled videos from scratch with multi-modal self-supervision, which learns clusters from multi-modal data in a self-supervised way.

facebookresearch/Ego-Exo: Code accompanying Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos (CVPR 2021)

facebookresearch/InvarianceUnitTests: Toy datasets to evaluate algorithms for domain generalization and invariance learning.

facebookresearch/RTFM: Experiment code for the ICLR 2020 paper "RTFM: Generalising to New Environment Dynamics via Reading".

facebookresearch/DisCo: DisCo Transformer for Non-autoregressive MT

facebookresearch/fastText: Library for fast text representation and classification.

facebookresearch/minihack: MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research

facebookresearch/deepfloat: An exploration of log domain "alternative floating point" for hardware ML/AI accelerators.

facebookresearch/worldsheet: Code release for the paper “Worldsheet Wrapping the World in a 3D Sheet for View Synthesis from a Single Image”, ICCV 2021.

facebookresearch/ContextualBanditsAttacks: Code supporting the paper Adversarial Attacks on Contextual Bandits accepted at Neurips 2020.

facebookresearch/svinfer: The FORT team has released differentially private Condor data to external researchers in H1 2020. It is known that analyzing DP data via classic statistical models will lead to biased conclusions. We are releasing at-scale statistical models which provide valid inference from DP data.

facebookresearch/drqv2: DrQ-v2: Improved Data-Augmented Reinforcement Learning

facebookresearch/deepmeg-recurrent-encoder: deepmeg recurrent encoder

facebookresearch/ParlAI: A framework for training and evaluating AI models on a variety of openly available dialogue datasets.

facebookresearch/graph2nn: code for paper "Graph Structure of Neural Networks"

facebookresearch/SingleModelUncertainty: Learning error bars for neural network predictions

facebookresearch/torcharrow: A machine learning preprocessing library over batch data, providing performant and Pandas-style easy-to-use API for model development

facebookresearch/vissl: VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

facebookresearch/DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation

facebookresearch/daqa: Temporal Reasoning via Audio Question Answering

facebookresearch/UnsupervisedQA: Unsupervised Question answering via Cloze Translation

facebookresearch/functorch: functorch is a prototype of JAX-like composable function transforms for PyTorch.

facebookresearch/videoalignment: Learning to align and match videos with kernelized temporal layers

facebookresearch/classifier-balancing: This repository contains code for the paper "Decoupling Representation and Classifier for Long-Tailed Recognition", published at ICLR 2020

facebookresearch/narwhal: Narwhal and Tusk: A DAG-based Mempool and Efficient BFT Consensus.

facebookresearch/UnsupervisedMT: Phrase-Based & Neural Unsupervised Machine Translation

facebookresearch/param: PArametrized Recommendation and Ai Model benchmark is a repository for development of numerous uBenchmarks as well as end to end nets for evaluation of training and inference platforms.

facebookresearch/BinauralSpeechSynthesis: N/A

facebookresearch/qhoptim: Implementations of quasi-hyperbolic optimization algorithms.

facebookresearch/ELI5: Scripts and links to recreate the ELI5 dataset.

facebookresearch/kbc: Tools for state of the art Knowledge Base Completion.

facebookresearch/beanmachine: A library that allows for inference on probabilistic models

facebookresearch/TimeSformer: The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"

facebookresearch/iSDF: Real-time Neural Signed Distance Fields for Robot Perception

facebookresearch/ResNeXt: Implementation of a classification framework from the paper Aggregated Residual Transformations for Deep Neural Networks

facebookresearch/Motionformer: Code + pre-trained models for the paper Keeping Your Eye on the Ball Trajectory Attention in Video Transformers

facebookresearch/SemanticImageTranslation: Evaluation benchmark for the task of Semantic Image Translation. Contains code to run FlexIT (CVPR 2022)

facebookresearch/ego-topo: Code accompanying EGO-TOPO: Environment Affordances from Egocentric Video (CVPR 2020)

facebookresearch/mpcfp: This is code associated with the paper, "Secure multiparty computations in floating-point arithmetic," published in the Institute of Mathematics and its Applications' "Information and Inference: a Journal of the IMA."

facebookresearch/DialogStitch: DialogStitch Synthetic Deeper and Multi-Context Task-Oriented Dialogs

facebookresearch/URL-Sanitization: The code processes URLs in an attempt to consolidate different web addresses that point to the same URL and to remove potentially private and/or sensitive data. It is part of the Facebook URL shares release effort, which is led by Election Research Commission (ERC).

facebookresearch/SIMAT: codebase for the SIMAT dataset and evaluation

facebookresearch/GENRE: Autoregressive Entity Retrieval

facebookresearch/LA-MCTS: High dimensional black-box optimizer using Latent Action Monte Carlo Tree Search algorithm

facebookresearch/multihop_dense_retrieval: Multi-hop dense retrieval for question answering

facebookresearch/m-amr2text: Generate from English-Centric AMR into Multiple Languages.

facebookresearch/imvotenet: ImVoteNet: Boosting 3D Object Detection in Point Clouds With Image Votes

facebookresearch/Augur: Augur is a machine learning system that provides per-layer inference performance and energy cost of running a NN layer on a consumer grade commercial NN accelerator.

facebookresearch/GDT: We present a framework for training multi-modal deep learning models on unlabelled video data by forcing the network to learn invariances to transformations applied to both the audio and video streams.

facebookresearch/pysparnn: Approximate Nearest Neighbor Search for Sparse Data in Python!

facebookresearch/dadc-limit: DADC in the Limit

facebookresearch/OctConv: Code for paper

facebookresearch/nonrigid_nerf: Open 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'.

facebookresearch/HVVR: Hierarchical Visibility for Virtual Reality, which implements a hybrid CPU/GPU ray-caster, suited for real time rendering of effects such as lens distortion.

facebookresearch/d2go: D2Go is a toolkit for efficient deep learning

facebookresearch/PoseWarper: Learning Temporal Pose Estimation from Sparsely Labeled Videos

facebookresearch/DONERF: Code for "DONeRF Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networks"

facebookresearch/DataEfficientNLG: NLG Best Practices for Data-Efficient Modeling How to Train Production-Ready Models with Little Data

facebookresearch/exploring_exploration: This paper contains code for our work "An Exploration of Embodied Visual Exploration".

facebookresearch/SRNN: A machine learning system that captures the dynamics of physical systems on the basis of observed trajectories via Hamiltionian modeling and symplectic integration.

facebookresearch/analyzing-uncertainty-nmt: Analyzing Uncertainty in Neural Machine Translation

facebookresearch/code-prediction-transformer: This repo will contain replication package for the paper "Feeding Trees to Transformers for Code Completion"

facebookresearch/fbcddisgraph: The codes reproduce the figures and statistics in the paper, "A graphical method of cumulative differences between two subpopulations," by Mark Tygert. The repo also provides the LaTeX and BibTex sources required for replicating the paper.

facebookresearch/hsd3: Code for "Hierarchical Skills for Efficient Exploration" HSD-3 Algorithm and Baselines

facebookresearch/bipedal-skills: Bipedal Skills Benchmark for Reinforcement Learning

facebookresearch/SAFEtorch: pytorch version of the SAFE neural network

facebookresearch/Replica-Dataset: The Replica Dataset v1 as published in https://arxiv.org/abs/1906.05797 .

facebookresearch/street-addresses: Robocodes: Towards Generative Street Addresses from Satellite Imagery

facebookresearch/ClassyVision: An end-to-end PyTorch framework for image and video classification

facebookresearch/robust_cvd: Robust Consistent Video Depth Estimation

facebookresearch/grid-feats-vqa: Grid features pre-training code for visual question answering

facebookresearch/off-belief-learning: Implementation of the Off Belief Learning algorithm.

facebookresearch/bernoulli_lse: Look-Ahead Acquisition Functions for Bernoulli Level Set Estimation

facebookresearch/AVID-CMA: Audio Visual Instance Discrimination with Cross-Modal Agreement

facebookresearch/fine_grained_hateful_memes: Fine grained annotations extending hateful memes dataset with additional labels for identifying protected categories and attack types.

facebookresearch/label_dp_antipodes: Code to reproduce experiments in "Antipodes of Label Differential Privacy PATE and ALIBI"

facebookresearch/DLRM-FlexFlow: Development repository for integrating FlexFlow (A distributed deep learning framework that supports flexible parallelization strategies) with DLRM (Deep Learning Recommendation Model)

facebookresearch/digit-design: Design files for the DIGIT tactile sensor

facebookresearch/mvp: Training and Evaluation Code for "Mixture of Volumetric Primitives for Efficient Neural Rendering"

facebookresearch/ppuda: Code for Parameter Prediction for Unseen Deep Architectures (NeurIPS 2021)

facebookresearch/tbsm: Time-based Sequence Model for Personalization and Recommendation Systems

facebookresearch/PyTouch: PyTouch is a machine learning library for tactile touch sensing.

facebookresearch/gala: Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning

facebookresearch/text-simplification-evaluation: Reference-less Quality Estimation of Text Simplification Systems

facebookresearch/pplbench: Evaluation Framework for Probabilistic Programming Languages

facebookresearch/contriever: Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning

facebookresearch/convit: Code for the Convolutional Vision Transformer (ConViT)

facebookresearch/body2hands: A method to estimate 3D hand gestures from 3D body motion input in body languages.

facebookresearch/polymetis: Write PyTorch controllers, test them in simulation, and seamlessly transfer to real-time hardware.

facebookresearch/vizseq: An Analysis Toolkit for Natural Language Generation (Translation, Captioning, Summarization, etc.)

facebookresearch/speech-resynthesis: An official reimplementation of the method described in the INTERSPEECH 2021 paper - Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.

facebookresearch/TensorComprehensions: A domain specific language to express machine learning workloads.

facebookresearch/odin: A simple and effective method for detecting out-of-distribution images in neural networks.

facebookresearch/LaMCTS: The release codes of LA-MCTS with its application to Neural Architecture Search.

facebookresearch/em-pose: EM-POSE 3D Human Pose Estimation from Sparse Electromagnetic Trackers. This repository contains the code to our paper published at ICCV 2021: https//ait.ethz.ch/projects/2021/em-pose

facebookresearch/CTrLBenchmark: Benchmark for Lifelong learning research

facebookresearch/hgnn: Hyperbolic Graph Neural Networks

facebookresearch/OTTER: This code provides a PyTorch implementation for OTTER (Optimal Transport distillation for Efficient zero-shot Recognition), as described in the paper.

facebookresearch/shaDow_GNN: NeurIPS 2021: Improve the GNN expressivity and scalability by decoupling the depth and receptive field of state-of-the-art GNN architectures

facebookresearch/MT-EQA: Multi-Target Embodied Question Answering

facebookresearch/RRL: Code for RRL (https://sites.google.com/view/abstractions4rl)

facebookresearch/.github: Default Community health files for Facebook projects

facebookresearch/AR-Depth: Fast Depth Densification for Occlusion-Aware Augmented Reality

facebookresearch/LeViT: LeViT a Vision Transformer in ConvNet's Clothing for Faster Inference

facebookresearch/relative_pose_dataset: We release a dataset that we have generated from TUM benchmark to evaluate relative pose estimators and therefore facilitate the comparison against future solutions for the relative pose problem.

facebookresearch/pifuhd: High-Resolution 3D Human Digitization from A Single Image.

facebookresearch/sound-spaces: A first-of-its-kind acoustic simulation platform for audio-visual embodied AI research. It supports training and evaluating multiple tasks and applications.

facebookresearch/neuralvolumes: Training and Evaluation Code for Neural Volumes

facebookresearch/Project_FARSI: We will be open sourcing a tool called FARSI (Facebook AR system investigator), a design space exploration framework. FARSI enables an agile and automated search of optimal hardware allocation and software-to-hardware mapping solutions.

facebookresearch/Addressing-the-Topological-Defects-of-Disentanglement: Repo reproducing experimental results in "Addressing the Topological Defects of Disentanglement"

facebookresearch/taskmodularnets: A set of neural network modules, which are small fully connected layers operating in semantic concept space. These modules are configured through a gating function conditioned on the task to produce features representing the compatibility between the input image and the concept under consideration.

facebookresearch/py2bpf: A python to bpf (Berkeley Packet Filter bytecode) converter

facebookresearch/SpanBERT: Code for using and evaluating SpanBERT.

facebookresearch/ContrastiveSceneContexts: Code for CVPR 2021 oral paper "Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts"

facebookresearch/DensePose: A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body

facebookresearch/Zero-Shot-DST: Zero-shot dialogue state tracking (DST)

facebookresearch/AdversarialAndDimensionality: First-Order Adversarial Vulnerability of Neural Networks and Input Dimension

facebookresearch/pybulletX: The lightweight PyBullet wrapper for robotics researchers. Scale your research with less boilerplate.

facebookresearch/QA-Overlap: Code to support the paper "Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets"

facebookresearch/bitsandbytes: Library for 8-bit optimizers and quantization routines.

facebookresearch/Clinical-Trial-Parser: Library for converting clinical trial eligibility criteria to a machine-readable format.

facebookresearch/nuanced: NUANCED is a user-centric conversational recommendation dataset that contains 5.1k annotated dialogues and 26k high-quality user turns.

facebookresearch/fairscale: PyTorch extensions for high performance and large scale training.

facebookresearch/mtrl: Multi Task RL Baselines

facebookresearch/neural-rewriter: Learning to Perform Local Rewriting for Combinatorial Optimization

facebookresearch/jacobian_regularizer: A pytorch implementation of our jacobian regularizer to encourage learning representations more robust to input perturbations.

facebookresearch/CodeGen: Reference implementation of code generation projects from Facebook AI Research. General toolkit to apply machine learning to code, from dataset creation to model training and evaluation. Comes with pretrained models.

facebookresearch/HyperNetworkDecoder: Hyper Graph Network Decoders for Block Codes

facebookresearch/agem: Official implementation of the Averaged Gradient Episodic Memory (A-GEM) in Tensorflow

facebookresearch/mvfst-rl: An asynchronous RL platform for congestion control in QUIC transport protocol. https://arxiv.org/abs/1910.04054.

facebookresearch/WavAugment: A library for speech data augmentation in time-domain

facebookresearch/MUSE: A library for Multilingual Unsupervised or Supervised word Embeddings

facebookresearch/gtn: Automatic differentiation with weighted finite-state transducers.

facebookresearch/neural-scs: Neural Fixed-Point Acceleration for Convex Optimization

facebookresearch/CommAI-env: A platform for developing AI systems as described in A Roadmap towards Machine Intelligence - http://arxiv.org/abs/1511.08130

facebookresearch/pytorch_GAN_zoo: A mix of GAN implementations including progressive growing

facebookresearch/PyTorch-BigGraph: Generate embeddings from large-scale graph-structured data.

facebookresearch/noise-as-targets: Unsupervised Learning by Predicting Noise

facebookresearch/LASER: Language-Agnostic SEntence Representations

facebookresearch/SWAG: Official repository for "Revisiting Weakly Supervised Pre-Training of Visual Perception Models". https://arxiv.org/abs/2201.08371.

facebookresearch/alma: Anytime Learning At Macroscale

facebookresearch/Hanabi_SPARTA: Research code implementing the search AI agent for Hanabi, as well as a web server so people can play against it

facebookresearch/transformer-sequential: Trains Transformer model variants. Data isn't shuffled between batches.

facebookresearch/SlowFast: PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

facebookresearch/meshtalk: Code for MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement

facebookresearch/MTRF: Code for MTRF (https://sites.google.com/view/mtrf)

facebookresearch/DPR: Dense Passage Retriever - is a set of tools and models for open domain Q&A task.

facebookresearch/suncet: Code to reproduce the results in the FAIR research papers "Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples" https://arxiv.org/abs/2104.13963 and "Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations" https://arxiv.org/abs/2006.10803

facebookresearch/loop_tool: A thin, highly portable toolkit for efficiently compiling dense loop-based computation.

facebookresearch/supervised-hashing-baselines: How should we evaluate supervised hashing

facebookresearch/mobile-vision: Mobile vision models and code

facebookresearch/NeuralCompression: A collection of tools for neural compression enthusiasts.

facebookresearch/TaBERT: This repository contains source code for the TaBERT model, a pre-trained language model for learning joint representations of natural language utterances and (semi-)structured tables for semantic parsing. TaBERT is pre-trained on a massive corpus of 26M Web tables and their associated natural language context, and could be used as a drop-in replacement of a semantic parsers original encoder to compute representations for utterances and table schemas (columns).

facebookresearch/vocoder-benchmark: A repository for benchmarking neural vocoders by their quality and speed.

facebookresearch/habitat-challenge: Code for the habitat challenge

facebookresearch/gtn_applications: Applications using the GTN library and code to reproduce experiments in "Differentiable Weighted Finite-State Transducers"

facebookresearch/ReAgent: A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)

facebookresearch/textlesslib: Library for Textless Spoken Language Processing

facebookresearch/deepcluster: Deep Clustering for Unsupervised Learning of Visual Features

facebookresearch/torchdynamo: A Python-level JIT compiler designed to make unmodified PyTorch programs faster.

facebookresearch/fastMRI: A large-scale dataset of both raw MRI measurements and clinical MRI images.

facebookresearch/mmf: A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

facebookresearch/MaskFormer: Per-Pixel Classification is Not All You Need for Semantic Segmentation (NeurIPS 2021, spotlight)

facebookresearch/dp_compression: Code repo for the paper "Privacy-aware Compression for Federated Data Analysis".

facebookresearch/ConvNeXt-V2: Code release for ConvNeXt V2 model

facebookresearch/CutLER: Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation"

facebookresearch/AutoCAT: AutoCAT: Reinforcement Learning for Automated Exploration of Cache-Timing Attacks

facebookresearch/gtmf: The implementation of GTMF(Ground Truth Maturity Framework)

facebookresearch/paco: This repo contains documentation and code needed to use PACO dataset: data loaders and training and evaluation scripts for objects, parts, and attributes prediction models, query evaluation scripts, and visualization notebooks.

facebookresearch/dadaptation: D-Adaptation for SGD, Adam and AdaGrad

facebookresearch/MCC: Multiview Compressive Coding for 3D Reconstruction

facebookresearch/vq2d_cvpr: This repo contains the code for the recipe of the winning entry to the Ego4d VQ2D challenge at CVPR 2022.

facebookresearch/R3VIVAL: A Repository of Room Responses and 360 Videos of a Variable Acoustics Lab

facebookresearch/balance: The balance python package offers a simple workflow and methods for dealing with biased data samples when looking to infer from them to some target population of interest.

facebookresearch/Whac-A-Mole: Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"

facebookresearch/NGDF: Neural Grasp Distance Fields for Robot Manipulation

facebookresearch/imu2clip: Code repository for IMU2CLIP(https//arxiv.org/pdf/2210.14395.pdf)

facebookresearch/e3b: Official repo for the E3B algorithm described in the paper "Exploration via Elliptical Episodic Bonuses".

facebookresearch/flashy: Framework for writing deep learning training loops. Lightweight, and retaining full freedom to design as you see fits. It handles checkpointing, logging, distributed, compatibility with Dora, and more!

facebookresearch/GPU-DPF: GPU-based Distributed Point Functions (DPF) and 2-server private information retrieval (PIR).

facebookresearch/hyperreel: Code release for HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling

facebookresearch/VideoPose3D: Efficient 3D human pose estimation in video using 2D keypoint trajectories

facebookresearch/vicreg: VICReg official code base

facebookresearch/SentAugment: SentAugment is a data augmentation technique for NLP that retrieves similar sentences from a large bank of sentences. It can be used in combination with self-training and knowledge-distillation, or for retrieving paraphrases.

facebookresearch/InterHand2.6M: Official PyTorch implementation of "InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image", ECCV 2020

facebookresearch/kill-the-bits: Code for: "And the bit goes down: Revisiting the quantization of neural networks"

facebookresearch/PointContrast: Code for paper <PointContrast: Unsupervised Pretraining for 3D Point Cloud Understanding>

facebookresearch/NARS: Scalable Graph Neural Networks for Heterogeneous Graphs

facebookresearch/hydra: Hydra is a framework for elegantly configuring complex applications

facebookresearch/shack: A shack for hacklang design

facebookresearch/RandomizedValueFunctions: Randomized Value Functions via Multiplicative Normalizing Flows

facebookresearch/svg: On the model-based stochastic value gradient for continuous reinforcement learning

facebookresearch/you2me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions

facebookresearch/GraphLog: API for accessing the GraphLog dataset

facebookresearch/theseus: A library for differentiable nonlinear optimization

facebookresearch/StarSpace: Learning embeddings for classification, retrieval and ranking.

facebookresearch/diplomacy_cicero: Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.

facebookresearch/DiT: Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

facebookresearch/tart: Code and model release for the paper "Task-aware Retrieval with Instructions" by Asai et al.

facebookresearch/NPM: The original implementation of Min et al. "Nonparametric Masked Language Modeling" (paper https//arxiv.org/abs/2212.01349)

facebookresearch/imagenetx: understanding model mistakes with human annotations

facebookresearch/LaViLa: Code release for "Learning Video Representations from Large Language Models"

facebookresearch/acs: Meta’s Anonymous Credential Service (ACS) is designed to enable it to authenticate users in a “de-identified manner,” permitting access to services without gathering any data that could be used to identify the subject’s identity.

facebookresearch/HolisticTraceAnalysis: A library to analyze PyTorch traces.

facebookresearch/w2ot: Euclidean Wasserstein-2 optimal transportation

facebookresearch/vsc2022: Code for the Video Similarity Challenge.

facebookresearch/mbr-exec: code for "Natural Language to Code Translation with Execution"

facebookresearch/isc2021: Code for the Image similarity challenge.

facebookresearch/Private-ID: A collection of algorithms that can do join between two parties while preserving the privacy of keys on which the join happens

facebookresearch/phyre-fwd: Code accompanying paper, Forward Prediction for Physical Reasoning

facebookresearch/EGG: EGG: Emergence of lanGuage in Games

facebookresearch/atlas: Code repository for supporting the paper "Atlas Few-shot Learning with Retrieval Augmented Language Models",(https//arxiv.org/abs/2208.03299)

facebookresearch/modem: MoDem Accelerating Visual Model-Based Reinforcement Learning with Demonstrations

facebookresearch/bart_ls: Long-context pretrained encoder-decoder models

facebookresearch/PLRC: Code for Point-Level Regin Contrast (https//arxiv.org/abs/2202.04639)

facebookresearch/ToMe: A method to increase the speed and lower the memory footprint of existing vision transformers.

facebookresearch/spoken_task_oriented_parsing: Spoken Task Oriented Parsing Dataset Page

facebookresearch/controllable_agent: The Controllable Agent project trains RL Agents able to optimize any reward function specified in real time, without any further learning or fine-tuning. Training is reward-free and based on the Forward-Backward representation.

facebookresearch/CODD: CODD ("Temporally Consistent Online Depth Estimation in Dynamic Scenes"), WACV 2023.

facebookresearch/SALSA: Source code for the paper SALSA Attacking Lattice Cryptography with Transformers (Wenger et al., Neurips 2022)

facebookresearch/symbolicregression: SR based on LLMs.

facebookresearch/minirts: We 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.

facebookresearch/go-fresh: Original code for the paper "Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping" by Mezghani et al.

facebookresearch/neural-conservation-law: code for "Neural Conservation Laws A Divergence-Free Perspective".

facebookresearch/entity-factored-rl: Source code for the paper "Policy Architectures for Compositional Generalization in Control"

facebookresearch/radioactive_data: This technique modifies image data so that any model trained on it will bear an identifiable mark.

facebookresearch/DeepFocus: DeepFocus: Learned Image Synthesis for Computational Displays

facebookresearch/detectron2: Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

facebookresearch/plush_dataset: This is the "plush" dataset associated with the CVPR 2022 paper "Virtual Elastic Objects".

facebookresearch/Kats: Kats, a kit to analyze time series data, a lightweight, easy-to-use, generalizable, and extendable framework to perform time series analysis, from understanding the key statistics and characteristics, detecting change points and anomalies, to forecasting future trends.

facebookresearch/StyleNeRF: This is the open source implementation of the ICLR2022 paper "StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis"

facebookresearch/recipes: Recipes are a standard, well supported set of blueprints for machine learning engineers to rapidly train models using the latest research techniques without significant engineering overhead.Specifically, recipes aims to provide- Consistent access to pre-trained SOTA models ready for production- Reference implementations for SOTA research reproducibility, and infrastructure to guarantee correctness, efficiency, and interoperability.

facebookresearch/TalkingWithHands32M: Talking with Hands

facebookresearch/AutoAvatar: AutoAvatar Autoregressive Neural Fields for Dynamic Avatar Modeling

facebookresearch/denoiser: Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is optimized on both time and frequency domains, using multiple loss functions. Empirical evidence shows that it is capable of removing various kinds of background noise including stationary and non-stationary noises, as well as room reverb. Additionally, we suggest a set of data augmentation techniques applied directly on the raw waveform which further improve model performance and its generalization abilities.

facebookresearch/coder_reviewer_reranking: Official code release for the paper Coder Reviewer Reranking for Code Generation.

facebookresearch/dagger: Experiment orchestration

facebookresearch/LAWT: Code for papers Linear Algebra with Transformers (TMLR) and What is my Math Transformer Doing? (AI for Maths Workshop, Neurips 2022)

facebookresearch/MeMViT: Code Release for MeMViT Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition, CVPR 2022

facebookresearch/3D-Vision-and-Touch: When told to understand the shape of a new object, the most instinctual approach is to pick it up and inspect it with your hand and eyes in tandem. Here, touch provides high fidelity localized information while vision provides complementary global context. However, in 3D shape reconstruction, the complementary fusion of visual and haptic modalities remains largely unexplored. In this paper, we study this problem and present an effective chart-based approach to fusing vision and touch, which leverages advances in graph convolutional networks. To do so, we introduce a dataset of simulated touch and vision signals from the interaction between a robotic hand and a large array of 3D objects. Our results show that (1) leveraging both vision and touch signals consistently improves single-modality baselines, especially when the object is occluded by the hand touching it; (2) our approach outperforms alternative modality fusion methods and strongly benefits from the proposed chart-based structure; (3) reconstruction quality boosts with the number of grasps provided; and (4) the touch information not only enhances the reconstruction at the touch site but also extrapolates to its local neighborhood.

facebookresearch/nds: On Network Design Spaces for Visual Recognition

facebookresearch/spotlight_hardware_designs: Partial set of hardware designs for a Meta-developed brain computer interface (BCI) research prototype system (Spotlight).

facebookresearch/ede: Code for the paper "Uncertainty-Driven Exploration for Generalization in Reinforcement Learning".

facebookresearch/c3dpo_nrsfm: C3DPO - Canonical 3D Pose Networks for Non-rigid Structure From Motion.

facebookresearch/mlqe: We release a dataset based on Wikipedia sentences and the corresponding translations in 6 different languages along with the scores (scale 1 to 100) generated though human evaluations that represent the quality of the translations.Paper Title Unsupervised Quality Estimation for Neural Machine Translation

facebookresearch/InvariantRiskMinimization: PyTorch code to run synthetic experiments.

facebookresearch/SyncMatch: Self-supervised Correspondence Estimation via Multiview Registration

facebookresearch/llama: Inference code for LLaMA models

facebookresearch/disentangling-correlated-factors: A benchmarking suite for disentanglement algorithms, suited for evaluating robustness to correlated factors. Codebase for the paper "Disentanglement of Correlated Factors via Hausdorff Factorized Support" by Karsten Roth, Mark Ibrahim, Zeynep Akata, Pascal Vincent, Diane Bouchacourt.

facebookresearch/FFCV-SSL: FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.

facebookresearch/AnimatedDrawings: Code to accompany "A Method for Animating Children's Drawings of the Human Figure"

facebookresearch/6DoF-Auraliser: An auralisation system that takes a head-worn microphone array recordings as input and renders the audio for binaural playback; taking into account both the listener's head-orientation and relative position from the recording point.

facebookresearch/where_to_begin: Repo to reproduce results for Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning

facebookresearch/FBTT-Embedding: This 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.

facebookresearch/PressureVision: [ECCV 2022] PressureVision: Estimating Hand Pressure from a Single RGB Image

facebookresearch/dragonclaw_library: code that goes with the dragonclaw paper

facebookresearch/InterWild: Official PyTorch implementation of "Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wild", CVPR 2023

facebookresearch/FashionPlus: Fashion++: Minimal Edits for Outfit Improvement

facebookresearch/FixRes: This repository reproduces the results of the paper: "Fixing the train-test resolution discrepancy" https://arxiv.org/abs/1906.06423

facebookresearch/OnlineAttacks: Study of a hypothetical attack scenario where an attacker corrupts images that are fed into an AI system, and has only a few chances before risking being detected.

facebookresearch/directclr: Code used in "Understanding Dimensional Collapse in Contrastive Self-supervised Learning" paper.

facebookresearch/Permutation-Equivariant-Seq2Seq: Humans understand novel sentences by composing meanings and roles of core language components. In contrast, neural network models for natural language modeling fail when such compositional generalization is required. The main contribution of this paper is to hypothesize that language compositionality is a form of group-equivariance. Based on this hypothesis, we propose a set of tools for constructing equivariant sequence-to-sequence models. Throughout a variety of experiments on the SCAN tasks, we analyze the behavior of existing models under the lens of equivariance, and demonstrate that our equivariant architecture is able to achieve the type compositional generalization required in human language understanding.

facebookresearch/FaderNetworks: Fader Networks: Manipulating Images by Sliding Attributes - NIPS 2017

facebookresearch/DME: Dynamic Meta-Embeddings for Improved Sentence Representations

facebookresearch/bio-lm: We evaluate many models used for biomedical and clinical nlp tasks, and train new models that perform much better.

facebookresearch/habitat-lab: A modular high-level library to train embodied AI agents across a variety of tasks and environments.

facebookresearch/foltr-es: The source code to reproduce the results reported in the 'Federated Online Learning to Rank with Evolution Strategies' paper, published at WSDM 2019.

facebookresearch/concurrentqa: This repo contains data and code for the paper "Reasoning over Public and Private Data in Retrieval-Based Systems."

facebookresearch/anli: Adversarial Natural Language Inference Benchmark

facebookresearch/MultiplexedOCR: Code for CVPR21 paper A Multiplexed Network for End-to-End, Multilingual OCR

facebookresearch/dynalab: The Python library with command line tools to interact with Dynabench(https://dynabench.org/), such as uploading models.

facebookresearch/habitat-matterport3d-dataset: This repository contains code to reproduce experimental results from our HM3D paper in NeurIPS 2021.

facebookresearch/Neural-Code-Search-Evaluation-Dataset: evaluation dataset consisting of natural language query and code snippet pairs

facebookresearch/td-delta: Separating value functions across time-scales.

facebookresearch/active_indexing: Official implementation of "Active Image Indexing"

facebookresearch/dropout: Code release for "Dropout Reduces Underfitting"

facebookresearch/OLLA: Optimizing the Lifetime and Location of Arrays to Reduce the Memory Usage of Neural Networks

facebookresearch/latent-space-priors: Source code release for "Leveraging Demonstrations with Latent Space Priors"

facebookresearch/visual-counterfactuals: Making Heads or Tails Towards Semantically Consistent Visual Counterfactuals

facebookresearch/pyvrs: Python interface for https//github.com/facebookresearch/vrs.

facebookresearch/dva: Drivable Volumetric Avatars

facebookresearch/diht: Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training

facebookresearch/Mask-Predict: A masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a partially masked target translation.

facebookresearch/rlr-audio-propagation: Audio propagation engine - Meta Reality Labs Research.

facebookresearch/cascade: Implementation of CASCADE in Learning General World Models in a Handful of Reward-Free Deployments (NeurIPS 22).

facebookresearch/home-robot: Low-level API for controlling various home robots

facebookresearch/aepsych: AEPsych is a tool for adaptive experimentation in psychophysics and perception research, built on top of gpytorch and botorch.

facebookresearch/voxelcnn: VoxelCNN: Order-Aware Generative Modeling Using the 3D-Craft Dataset

facebookresearch/muavic: MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation

facebookresearch/mbrl-lib: Library for Model Based RL

facebookresearch/rela: Reinforcement Learning Assembly

facebookresearch/VCMeshConv: Learning latent representations of registered meshes is useful for many 3D tasks. Techniques have recently shifted to neural mesh autoencoders. Although they demonstrate higher precision than traditional methods, they remain unable to capture fine-grained deformations. Furthermore, these methods can only be applied to a template-specific surface mesh, and is not applicable to more general meshes, like tetrahedrons and non-manifold meshes. While more general graph convolution methods can be employed, they lack performance in reconstruction precision and require higher memory usage. In this paper, we propose a non-template-specific fully convolutional mesh autoencoder for arbitrary registered mesh data. It is enabled by our novel convolution and (un)pooling operators learned with globally shared weights and locally varying coefficients which can efficiently capture the spatially varying contents presented by irregular mesh connections. Our model outperforms state-of-the-art methods on reconstruction accuracy. In addition, the latent codes of our network are fully localized thanks to the fully convolutional structure, and thus have much higher interpolation capability than many traditional 3D mesh generation models.

facebookresearch/recur: symbolic regression

facebookresearch/MidasTouch: MidasTouch: Monte-Carlo inference over distributions across sliding touch

facebookresearch/EDIN: This is the repo for the EMNLP 2022 paper 'EDIN An End-to-end Benchmark and Model for Unknown Entity Discovery and Indexing'.

facebookresearch/long_seq_mae: code release of research paper "Exploring Long-Sequence Masked Autoencoders"

facebookresearch/cycle_gan_for_complementary_item_recommendations: Research code of Cycle Generative Adversarial Networks for Complementary Item Recommendations.

facebookresearch/latticer: The codes reproduce the figures in the paper, "An efficient algorithm for integer lattice reduction." The repo also provides the LaTeX and BibTeX sources required for replicating the paper.

facebookresearch/cc_net: Tools to download and cleanup Common Crawl data

facebookresearch/PhysicsVAE: Physics-based Character Controllers Using Conditional VAEs (SIGGRAPH 2022)

facebookresearch/habitat-sim: A flexible, high-performance 3D simulator for Embodied AI research.

facebookresearch/NasRec: NASRec Weight Sharing Neural Architecture Search for Recommender Systems

facebookresearch/DeltaCNN: DeltaCNN End-to-End CNN Inference of Sparse Frame Differences in Videos

facebookresearch/CiT: Code for the paper titled "CiT Curation in Training for Effective Vision-Language Data".

facebookresearch/qEUBO: Reproducible code for paper "qEUBO A Decision-Theoretic Acquisition Function for Preferential Bayesian Optimization" from AISTATS 2023

facebookresearch/miniF2F: An updated version of miniF2F with lots of fixes and informal statements / solutions.

facebookresearch/SparseBO: code associated with paper "Sparse Bayesian Optimization"

facebookresearch/how-to-autorl: Plug-and-play hydra sweepers for the EA-based multifidelity method DEHB and several population-based training variations, all proven to efficiently tune RL hyperparameters.

facebookresearch/video-distant-supervision: This is an official pytorch implementation of Learning To Recognize Procedural Activities with Distant Supervision. In this repository, we provide PyTorch code for training and testing as described in the paper. The proposed distant supervision framework achieves strong generalization performance on step classification, recognition of procedural activities, step forecasting (New Task!) and egocentric activity classification.

facebookresearch/Blackbox-Coresets-VI: A suite for blackbox variational inference using families of posterior approximations parameterised via learnable weighted summarising (pseudo)data.

facebookresearch/XNLI: Evaluating Cross-lingual Sentence Representations

facebookresearch/level-replay: This code implements Prioritized Level Replay, a method for sampling training levels for reinforcement learning agents that exploits the fact that not all levels are equally useful for agents to learn from during training.

facebookresearch/DeepFovea: Neural Reconstruction for Foveated Rendering and Video Compression using Learned Statistics of Natural Videos

facebookresearch/MetaBalance: MetaBalance algorithm for multi-task learning

facebookresearch/gad: Generic Automatic Differentiation library for Rust (aka "autograd")

facebookresearch/splitnet: Code for SplitNet paper

facebookresearch/grounding-inductive-biases: reproduces experiments from "Grounding inductive biases in natural images: invariance stems from variations in data"

facebookresearch/calibration_membership: Public implementation of the paper "On the Importance of Difficulty Calibration in Membership Inference Attacks".

facebookresearch/hiplot: HiPlot makes understanding high dimensional data easy

facebookresearch/FriendshipSatisfactionDiversity: Replication code for "What Does Perception Bias on Social Networks Tell Us About Friend Count Satisfaction?", TheWebConf2022.

facebookresearch/ic_gan: Official repository for the paper "Instance-Conditioned GAN" by Arantxa Casanova, Marlene Careil, Jakob Verbeek, Michał Drożdżal, Adriana Romero-Soriano.

facebookresearch/unlikelihood_training: Neural Text Generation with Unlikelihood Training

facebookresearch/FAMBench: Benchmarks to capture important workloads.

facebookresearch/MetaICL: An original implementation of "MetaICL Learning to Learn In Context" by Sewon Min, Mike Lewis, Luke Zettlemoyer and Hannaneh Hajishirzi

facebookresearch/svoice: We provide a PyTorch implementation of the paper Voice Separation with an Unknown Number of Multiple Speakers In which, we present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.

facebookresearch/clevr-dataset-gen: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning

facebookresearch/fvcore: Collection of common code that's shared among different research projects in FAIR computer vision team.

facebookresearch/CarbonExplorer: Carbon Explorer helps evaluating solutions make datacenters operate on renewable energy.

facebookresearch/FDR_scheduler: Fluctuation-dissipation relations for stochastic gradient descent

facebookresearch/faiss: A library for efficient similarity search and clustering of dense vectors.

facebookresearch/TorchRay: Understanding Deep Networks via Extremal Perturbations and Smooth Masks

facebookresearch/astmt: Attentive Single-tasking of Multiple Tasks

facebookresearch/spreadingvectors: Open source implementation of "Spreading Vectors for Similarity Search"

facebookresearch/adversarially-motivated-intrinsic-goals: This repository contains code for the method and experiments of the paper "Learning with AMIGo: Adversarially Motivated Intrinsic Goals".

facebookresearch/ssl_watermarking: Official implementation of "Watermarking Images in Self-Supervised Latent-Spaces"

facebookresearch/CPC_audio: An implementation of the Contrast Predictive Coding (CPC) method to train audio features in an unsupervised fashion.

facebookresearch/banmo: BANMo Building Animatable 3D Neural Models from Many Casual Videos

facebookresearch/madgrad: MADGRAD Optimization Method

facebookresearch/digit-interface: Python interface for the DIGIT tactile sensor

facebookresearch/task_bench: The TaskBench500 dataset and code for generating tasks.

facebookresearch/CParser: A compact C preprocessor and declaration parser written in pure Lua

facebookresearch/DomainBed: DomainBed is a suite to test domain generalization algorithms

facebookresearch/robust_mobo: Code for "Robust Multi-Objective Bayesian Optimization Under Input Noise"

facebookresearch/Active-3D-Vision-and-Touch: A repository for the paper Active 3D Shape Reconstruction from Vision and Touch and robotic touch simulator package.

facebookresearch/DynamicsAware: Physical Reasoning Using Dynamics-Aware Models

facebookresearch/demucs: Code for the paper Hybrid Spectrogram and Waveform Source Separation

facebookresearch/Geo-metric: Geo-metric A Perceptual Dataset of Distortions on Faces" by Wolski et al., SIGGRAPH Asia 2022.

facebookresearch/ov-seg: This is the official PyTorch implementation of the paper Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP.

facebookresearch/encodec: State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.

facebookresearch/hanabi_SAD: Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning

facebookresearch/fairring: Fairring (FAIR + Herring) is a plug-in for PyTorch that provides a process group for distributed training that outperforms NCCL at large scales

facebookresearch/CCQA: CCQA A New Web-Scale Question Answering Dataset for Model Pre-Training

facebookresearch/speech_translation: Demo and samples for universal speech translator

facebookresearch/Clockwork: Recurring batch data pipelines are a staple of the modern enterprisescale data warehouse. As a data warehouse scales to support more products and services, a growing number of interdependent pipelines running at various cadences can give rise to periodic resource bottlenecks for a cluster. This resource contention results in pipelines starting at unpredictable times each day and consequently variable landing times for the data artifacts they produce. The variability gets compounded by the dependency structure of the workload, and the resulting unpredictability can disrupt the project workstreams which consume this data. We present Clockwork, a delay-based global scheduling framework for data pipelines which improves landing time stability by spreading out tasks throughout the day. Whereas most scheduling algorithms optimize for makespan or average job completion times, Clockwork’s execution plan optimizes for stability in task completion times while also targeting predifined pipeline. Online experiments comparing this novel scheduling algorithm and a previously proposed greedy procrastinating heurstic show tasks complete almost an hour earlier on average, while exhibiting lower landing time variance and producing significantly less competition for resources in a target cluster.

facebookresearch/differentiable-robot-model: We 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.

facebookresearch/maskrcnn-benchmark: Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

facebookresearch/data2vec_vision: Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

facebookresearch/fbpcf: Private computation framework library allows developers to perform randomized controlled trials, without leaking information about who participated or what action an individual took. It uses secure multiparty computation to guarantee this privacy. It is suitable for conducting A/B testing, or measuring advertising lift and learning the aggregate statistics without sharing information on the individual level.

facebookresearch/many-to-many-dijkstra: A predictive model developed to identify medium-voltage electrical distribution grid infrastructure using publicly available data sources.

facebookresearch/d3d-hoi: We create D3D-HOI a dataset of monocular videos with ground truth annotations of 3D object pose and part motion during human-object interaction.

facebookresearch/pytorch3d: PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

facebookresearch/dino: PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

facebookresearch/qmnist: The QMNIST dataset

facebookresearch/M3RL: Mind-aware Multi-agent Management Reinforcement Learning

facebookresearch/dcem: The Differentiable Cross-Entropy Method

facebookresearch/clutrr: Diagnostic benchmark suite to explicitly test logical relational reasoning on natural language

facebookresearch/vilbert-multi-task: Multi Task Vision and Language

facebookresearch/augmentation-corruption: This repository provides code for "On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness".

facebookresearch/r3m: Pre-training Reusable Representations for Robotic Manipulation Using Diverse Human Video Data

facebookresearch/dlrm_datasets: Set of datasets for the deep learning recommendation model (DLRM).

facebookresearch/zest: Zest is a compression-based text classifier using Meta's Zstandard compression algorithm. Zest is language-agnostic and this approach simplifies configuration, avoids careful feature extraction and large ML models.

facebookresearch/detr: End-to-End Object Detection with Transformers

facebookresearch/mmd: ML models often mispredict, and it is hard to tell when and why. We present a data mining based approach to discover whether there is a certain form of data that particular causes the model to mispredict.

facebookresearch/preference-exploration: Code for replicating experiments from the paper, Preference Exploration for Efficient Bayesian Optimization with Multiple Outcomes, published in AISTATS 2022.

facebookresearch/Needles-in-Haystacks: Needles in Haystacks: On Classifying Tiny Objects in Large Images

facebookresearch/simsiam: PyTorch implementation of SimSiam https//arxiv.org/abs/2011.10566

facebookresearch/image-goal-nav-dataset: Dataset for Image-Goal Navigation in Habitat

facebookresearch/bounding_data_reconstruction: Repo for the paper "Bounding Training Data Reconstruction in Private (Deep) Learning".

facebookresearch/Noresqa: This github repo is for Neurips 2021 and Interspeech 2022 papers on Non-Matching Reference based estimation of speech quality assessment.

facebookresearch/Ad-Library-API-Script-Repository: GitHub repository of commonly used python scripts that allows everyone to pull data via the Ad Library API

facebookresearch/distributed-faiss: A library for building and serving multi-node distributed faiss indices.

facebookresearch/productive_concept_learning: Code for the benchmark containing dataset, models and metrics for productive concept learning -- a kind of compositional reasoning task that requires reasoning about uncertainty and learning compositionally rich and challenging concepts in a low-shot, meta-learning framework.

facebookresearch/TransCoder: Public release of the TransCoder research project https://arxiv.org/pdf/2006.03511.pdf

facebookresearch/facestar: Facestar dataset. High quality audio-visual recordings of human conversational speech.

facebookresearch/talkthewalk: This 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.

facebookresearch/dachshund: Dachshund is a graph mining library written in Rust. It provides high performance data structures for multiple kinds of graphs, from simple undirected graphs to typed hypergraphs. Dachshund also provides algorithms for common tasks for graph mining and analysis, ranging from shortest paths to graph spectral analysis.

facebookresearch/privacy_lint: Lint for privacy

facebookresearch/iopath: A python library that provides common I/O interface across different storage backends.

facebookresearch/irt-leaderboard: Leaderboards are widely used in NLP and push the field forward. While leaderboards are a straightforward ranking of NLP models, this simplicity can mask nuances in evaluation items (examples) and subjects (NLP models). Rather than replace leaderboards, we advocate a re-imagining so that they better highlight if and where progress is made. Building on educational testing, we create a Bayesian leaderboard where latent subject skill and latent item difficulty predict correct responses. Using this model, we analyze the reliability of leaderboards. Afterwards, we show the model can guide what annotate, identify annotation errors, detect overfitting, and identify informative examples.

facebookresearch/jps: Code for "Joint Policy Search for Collaborative Multi-agent Incomplete Information Games"

facebookresearch/sscd-copy-detection: Open source implementation of "A Self-Supervised Descriptor for Image Copy Detection" (SSCD).

facebookresearch/BalancingGroups: Simple data balancing baselines for worst-group-accuracy benchmarks.

facebookresearch/soundspaces-challenge: Starter code for SoundSpaces challenge at CVPR 21's Embodied AI workshop

facebookresearch/ss3d: Code release for "Pre-train, Self-train, Distill A simple recipe for Supersizing 3D Reconstruction"

facebookresearch/MLDoc: A Corpus for Multilingual Document Classification in Eight Languages.

facebookresearch/modeling_long_term_future: Code for ICLR 2019 paper Learning Dynamics Model by Incorporating the Long Term Future

facebookresearch/LearningToLearn: Collection of algorithms to learn loss and reward functions via gradient-based bi-level optimization.

facebookresearch/dietgpu: GPU implementation of a fast generalized ANS (asymmetric numeral system) entropy encoder and decoder, with extensions for lossless compression of numerical and other data types in HPC/ML applications.

facebookresearch/metaseq: Repo for external large-scale work

facebookresearch/frankmocap: A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator

facebookresearch/accentor: Data & Code for ACCENTOR: "Adding Chit-Chat to Enhance Task-Oriented Dialogues" (NAACL 2021)

facebookresearch/fairseq: Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

facebookresearch/MathsFromExamples: Source code, datasets and trained models for the paper Learning Advanced Mathematical Computations from Examples (ICLR 2021), by François Charton, Amaury Hayat (ENPC-Rutgers) and Guillaume Lample

facebookresearch/opendialkg: OpenDialKG: Explainable Conversational Reasoning with Attention-based Walks over Knowledge Graphs

facebookresearch/FAIR-Play: 2.5D visual sound dataset

facebookresearch/swav: PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882

facebookresearch/measuring-emergent-comm: On the pitfalls of measuring emergent communication

facebookresearch/DrQA: Reading Wikipedia to Answer Open-Domain Questions

facebookresearch/higher: higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

facebookresearch/multimodal: TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.

facebookresearch/mvit: Code Release for MViTv2 on Image Recognition.

facebookresearch/pytext: A natural language modeling framework based on PyTorch

facebookresearch/simmc: With 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.

facebookresearch/tacto: Simulator of vision-based tactile sensors.

facebookresearch/ActivityNet-Entities: A Dataset for Grounded Video Description

facebookresearch/IMGUR5K-Handwriting-Dataset: IMGUR5K handwriting set. It is a handwritten in-the-wild dataset, which contains challenging real world handwritten samples from different writers.The dataset is shared as a set of image urls with annotations. This code downloads the images and verifies the hash to the image to avoid data contamination.

facebookresearch/asynchronousratchetingtree: On Ends-to-Ends Encryption: Asynchronous Group Messaging with Strong Security Guarantees

facebookresearch/nle: The NetHack Learning Environment

facebookresearch/diffq: DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight or group of weights, in order to achieve a given trade-off between model size and accuracy.

facebookresearch/moco-v3: PyTorch implementation of MoCo v3 https//arxiv.org/abs/2104.02057

facebookresearch/adaptive-softmax: Implements an efficient softmax approximation as described in the paper "Efficient softmax approximation for GPUs" (http://arxiv.org/abs/1609.04309)

facebookresearch/OccupancyAnticipation: This repository contains code for our publication "Occupancy Anticipation for Efficient Exploration and Navigation" in ECCV 2020.

facebookresearch/RidgeSfM: Ridge SfM Structure from Motion via robust pairwise matching under depth uncertainty

facebookresearch/muss: Code and models used in "MUSS Multilingual Unsupervised Sentence Simplification by Mining Paraphrases".

facebookresearch/open_lth: A repository in preparation for open-sourcing lottery ticket hypothesis code.

facebookresearch/fairseq-lua: Facebook AI Research Sequence-to-Sequence Toolkit

facebookresearch/mega: Sequence modeling with Mega.

facebookresearch/VICRegL: VICRegL official code base

facebookresearch/TCDM: Code release for "Learning Dexterous Manipulation from Exemplar Object Trajectories and Pre-Grasps"

facebookresearch/canife: Crafting canaries to measure empirical privacy of DP-FL training under a realistic threat model.

facebookresearch/Uncertainty-Driven-Active-Vision: Companion code for "Uncertainty-Driven Active Vision for Implicit Scene Reconstruction". This repository contains the code base for a Next Best View (NBV) task along with our proposed uncertainty driven solution and a set of baselines for comparison.

facebookresearch/collaborative_image_understanding: Collaborative Image Understanding leveraging collaborative information to improve image classifiers.

facebookresearch/bit: Code repo for the paper BiT Robustly Binarized Multi-distilled Transformer

facebookresearch/covost: CoVoST: A Large-Scale Multilingual Speech-To-Text Translation Corpus (CC0 Licensed)

facebookresearch/rlstructures: RLStructures is a library to facilitate the implementation of new reinforcement learning algorithms. It includes a library, a tutorial, and different RL algorithms provided as examples.

facebookresearch/eft: visualization code for 3D human body annotation by EFT (Exemplar Fine-tuning)

facebookresearch/multipathnet: A Torch implementation of the object detection network from "A MultiPath Network for Object Detection" (https://arxiv.org/abs/1604.02135)

facebookresearch/nevergrad: A Python toolbox for performing gradient-free optimization

facebookresearch/music-translation: A UNIVERSAL MUSIC TRANSLATION NETWORK - a method for translating music across musical instruments and styles.

facebookresearch/Listen-to-Look: Listen to Look: Action Recognition by Previewing Audio (CVPR 2020)

facebookresearch/moco: PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

facebookresearch/dora: Dora is an experiment management framework. It expresses grid searches as pure python files as part of your repo. It identifies experiments with a unique hash signature. Scale up to hundreds of experiments without losing your sanity.

facebookresearch/nbref: Codebase for paper "N-Bref A High-fidelity Decompiler Exploiting Programming Structures"

facebookresearch/unbiased-teacher: PyTorch code for ICLR 2021 paper Unbiased Teacher for Semi-Supervised Object Detection

facebookresearch/semi-supervised-ImageNet1K-models: Semi-supervised ImageNet1K models

facebookresearch/meta_seq2seq: Compositional generalization through meta sequence-to-sequence learning

facebookresearch/rebel: An algorithm that generalizes the paradigm of self-play reinforcement learning and search to imperfect-information games.

facebookresearch/fbpcp: FBPCP (Facebook Private Computation Platform) is a secure, privacy safe and scalable architecture to deploy MPC (Multi Party Computation) applications in a distributed way on virtual private clouds. FBPCF (Facebook Private Computation Framework) is for scaling MPC computation up via threading, while FBPCP is for scaling MPC computation out via Private Scaling architecture.

facebookresearch/supervision-by-registration: Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors

facebookresearch/dpr-scale: Scalable training for dense retrieval models.

facebookresearch/AugLy: A data augmentations library for audio, image, text, and video.

facebookresearch/rcpm: Riemannian Convex Potential Maps

facebookresearch/CovidPrognosis: COVID deterioration prediction based on chest X-ray radiographs via MoCo-trained image representations

facebookresearch/salina: a Lightweight library for sequential learning agents, including reinforcement learning

facebookresearch/SLIP: Code release for SLIP Self-supervision meets Language-Image Pre-training

facebookresearch/neural_stpp: Deep generative modeling for time-stamped heterogeneous data, enabling high-fidelity models for a large variety of spatio-temporal domains.

facebookresearch/DetectAndTrack: The implementation of an algorithm presented in the CVPR18 paper: "Detect-and-Track: Efficient Pose Estimation in Videos"

facebookresearch/InferSent: InferSent sentence embeddings

facebookresearch/DepthContrast: DepthContrast self-supervised learning for 3D

facebookresearch/pytorchvideo: A deep learning library for video understanding research.

facebookresearch/CrypTen: A framework for Privacy Preserving Machine Learning

facebookresearch/FLSim: Federated Learning Simulator (FLSim) is a flexible, standalone core library that simulates FL settings with a minimal, easy-to-use API. FLSim is domain-agnostic and accommodates many use cases such as vision and text.

facebookresearch/deit: Official DeiT repository

facebookresearch/darkforestGo: DarkForest, the Facebook Go engine.

facebookresearch/SymbolicMathematics: Deep Learning for Symbolic Mathematics

facebookresearch/mtenv: MultiTask Environments for Reinforcement Learning.

facebookresearch/voxpopuli: A large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation

facebookresearch/inversecooking: Recipe Generation from Food Images

facebookresearch/CompilerGym: Reinforcement learning environments for compiler and program optimization tasks

facebookresearch/Adversarial-Continual-Learning: Implementation for the paper "Adversarial Continual Learning" in PyTorch.

facebookresearch/labgraph: LabGraph is a Python framework for rapidly prototyping experimental systems for real-time streaming applications. It is particularly well-suited to real-time neuroscience, physiology and psychology experiments.

facebookresearch/AVT: Code release for ICCV 2021 paper "Anticipative Video Transformer"

facebookresearch/video-nonlocal-net: Non-local Neural Networks for Video Classification

facebookresearch/mae_st: Official Open Source code for "Masked Autoencoders As Spatiotemporal Learners"

facebookresearch/EditEval: An instruction-based benchmark for text improvements.

facebookresearch/Data_Acquisition_for_ML_Benchmark: DAM Data Acquisition for ML Benchmark, as part of the DataPerf benchmark suite, https://dataperf.org/

facebookresearch/torchbeast: A PyTorch Platform for Distributed RL

facebookresearch/Ego4d: Ego4d dataset repository. Download the dataset, visualize, extract features & example usage of the dataset

facebookresearch/latent-treelstm: Cooperative Learning of Disjoint Syntax and Semantics

facebookresearch/VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency

facebookresearch/xformers: Hackable and optimized Transformers building blocks, supporting a composable construction.

facebookresearch/UnsupervisedDecomposition: PyTorch original implementation of "Unsupervised Question Decomposition for Question Answering"

facebookresearch/DeepHandMesh: Official PyTorch implementation of "DeepHandMesh: A Weakly-Supervised Deep Encoder-Decoder Framework for High-Fidelity Hand Mesh Modeling," ECCV 2020

facebookresearch/deep_bisim4control: Learning Invariant Representations for Reinforcement Learning without Reconstruction

facebookresearch/end-to-end-negotiator: Deal or No Deal? End-to-End Learning for Negotiation Dialogues

facebookresearch/ssl-relation-prediction: Simple yet SoTA Knowledge Graph Embeddings.

facebookresearch/randsent: Exploring Random Encoders for Sentence Classification

facebookresearch/QuaterNet: Proposes neural networks that can generate animation of virtual characters for different actions.

facebookresearch/Mask2Former: Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

facebookresearch/flores: Facebook Low Resource (FLoRes) MT Benchmark

facebookresearch/PAQ: Code and data to support the paper "PAQ 65 Million Probably-Asked Questions andWhat You Can Do With Them"

facebookresearch/stochastic_gradient_push: Stochastic Gradient Push for Distributed Deep Learning

facebookresearch/SEAL_OGB: An open-source implementation of SEAL for link prediction in open graph benchmark (OGB) datasets.

facebookresearch/playtorch: PlayTorch is a framework for rapidly creating mobile AI experiences.

facebookresearch/Radlibrary: An R package for accessing the Facebook Ad Library API

facebookresearch/UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering

facebookresearch/consistent_depth: We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.

facebookresearch/adaptive_teacher: This repo provides the source code for "Cross-Domain Adaptive Teacher for Object Detection".

facebookresearch/SEAL: Search Engines with Autoregressive Language models

facebookresearch/msn: Masked Siamese Networks for Label-Efficient Learning (https://arxiv.org/abs/2204.07141)

facebookresearch/CMR: N/A

facebookresearch/pycls: Codebase for Image Classification Research, written in PyTorch.

facebookresearch/rlmeta: RLMeta is a light-weight flexible framework for Distributed Reinforcement Learning Research.

facebookresearch/gwil: Cross-Domain Imitation Learning via Optimal Transport

facebookresearch/NASViT: code for NASViT

facebookresearch/DistDepth: Repository for "Toward Practical Monocular Indoor Depth Estimation" (CVPR 2022)

facebookresearch/moe: Misspelling Oblivious Word Embeddings

facebookresearch/omnivore: Omnivore: A Single Model for Many Visual Modalities

facebookresearch/dcd: Implementations of robust Dual Curriculum Design (DCD) algorithms for unsupervised environment design.

facebookresearch/tan: Computationally friendly hyper-parameter search with DP-SGD

facebookresearch/vip: Official repository for "VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training"

facebookresearch/CPA: The Compositional Perturbation Autoencoder (CPA) is a deep generative framework to learn effects of perturbations at the single-cell level. CPA performs OOD predictions of unseen combinations of drugs, learns interpretable embeddings, estimates dose-response curves, and provides uncertainty estimates.

facebookresearch/synsin: View synthesis for the public.

facebookresearch/fbai-speech: Repo for the FB AI Speech team.

facebookresearch/perfect: PERFECT: Prompt-free and Efficient Few-shot Learning with Language Models

facebookresearch/morbo: Multi-Objective Bayesian Optimization over High-Dimensional Search Spaces

facebookresearch/HRViT: HRViT ("Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation"), CVPR 2022.

facebookresearch/denoised_mdp: Open source code for paper "Denoised MDPs: Learning World Models Better Than the World Itself"

facebookresearch/EasyComDataset: The Easy Communications (EasyCom) dataset is a world-first dataset designed to help mitigate the *cocktail party effect* from an augmented-reality (AR) -motivated multi-sensor egocentric world view.

facebookresearch/viewseg: Code for "Recognizing Scenes from Novel Viewpoints"

facebookresearch/taobench-data: This contains the data for the TaoBench benchmarking project. Adaptors to generate workloads from this data are available at https//github.com/audreyccheng/taobench.

facebookresearch/vsait: Unpaired Image Translation via Vector Symbolic Architectures (ECCV 2022)

facebookresearch/DoodlerGAN: AI models that can doodle/sketch

facebookresearch/reliable_vqa: Implementation for the paper "Reliable Visual Question Answering Abstain Rather Than Answer Incorrectly" (ECCV 2022: https//arxiv.org/abs/2204.13631).

facebookresearch/WSL-Images: Weakly Supervised Learning On Images

facebookresearch/Cupcake: A Rust library for lattice-based additive homomorphic encryption.

facebookresearch/MultipleAttributeTextRewriting: This paper shows how to rewrite text while controlling multiple attributes using techniques from back-translation.

facebookresearch/side: The AI Knowledge Editor

facebookresearch/Imppres: This repository houses the IMPlicature and PRESupposition diagnostic dataset (IMPPRES), consisting of >25k semiautomatically generated sentence pairs illustrating well-studied pragmatic inference types. IMPPRES is an NLI dataset following the format of SNLI (Bowman et al., 2015), MultiNLI (Williams et al., 2018) and XNLI (Conneau et al., 2018), which was created to determine how well trained NLI models do on recognizing several kinds of presuppositions and scalar implicatures.

facebookresearch/online-dt: Online Decision Transformer

facebookresearch/shumai: Fast Differentiable Tensor Library in JavaScript and TypeScript with Bun + Flashlight

facebookresearch/ACT: ACT An Architectural Carbon Modeling Tool for Designing Sustainable Computer Systems

facebookresearch/SecureFLCompression: Compression primitives for uplink compression in Federated Learning that are compatible with Secure Aggregation.

facebookresearch/text-adversarial-attack: Repo for arXiv preprint "Gradient-based Adversarial Attacks against Text Transformers"

facebookresearch/quip: Official repository for the paper "Question Answering Infused Pre-training of General-Purpose Contextualized Representations" by Robin Jia, Mike Lewis, and Luke Zettlemoyer.

facebookresearch/mudoco: A synthetic dataset of dialogs we authored and annotated for references (pronouns, etc.). This dataset is discussed in the paper "MuDoCo: Corpus for Multidomain Coreference Resolution and Referring Expression Generation", which appeared at LREC 2020.

facebookresearch/Detectron: FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

facebookresearch/AutoCTR: code for https//research.fb.com/publications/towards-automated-neural-interaction-discovery-for-click-through-rate-prediction/

facebookresearch/DVDialogues: Code for DVD A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue

facebookresearch/hypernymysuite: Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora

facebookresearch/reconsider: ReConsider is a re-ranking model that re-ranks the top-K (passage, answer-span) predictions of an Open-Domain QA Model like DPR (Karpukhin et al., 2020).

facebookresearch/social-catalysts: We introduce the notion of a social catalyst in the context of social media a person who prompts interaction between their friends through their posts. We find not only that this activity is heavily skewed, but that it also correlates with participation in groups and events. We validate the behavioral measure using a survey wherein people nominate social catalysts in their friend network. Whether a person will be nominated as a social catalyst can be predicted using network features and the tendency of their posts to prompt discussion. Although individuals' role as social catalysts has not attracted much study to date, this paper demonstrates that it can be studied both via behavioral and survey measures.

facebookresearch/wsd-biencoders: Experiment code for the ACL 2020 paper "Moving Down the Long Tail of Word Sense Disambiguation with Gloss Informed Bi-encoders".

facebookresearch/Sphere: Web-scale retrieval for knowledge-intensive NLP

facebookresearch/neuromorph: Implementation of the NeuroMorph method from CVPR 2021.

facebookresearch/AudioMAE: This repo hosts the code and models of "Masked Autoencoders that Listen".

facebookresearch/DepthShrinker: [ICML 2022] "DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks", by Yonggan Fu, Haichuan Yang, Jiayi Yuan, Meng Li, Cheng Wan, Raghuraman Krishnamoorthi, Vikas Chandra, Yingyan Lin

facebookresearch/CausalSkillLearning: Codebase for project about unsupervised skill learning via variational inference and causality.

facebookresearch/multiface: Hosts the Multiface dataset, which is a multi-view dataset of multiple identities performing a sequence of facial expressions.

facebookresearch/stopes: A library for preparing data for machine translation research (monolingual preprocessing, bitext mining, etc.) built by the FAIR NLLB team.

facebookresearch/baspacho: Direct solver for symmetric positive-definite sparse matrices designed for mathematical optimization. It implements supernodal Cholesky decomposition algorithm, and has GPU support.

facebookresearch/RCDM: Visualizing representations with diffusion based conditional generative model.

facebookresearch/RF2: RF^2 is a federated recommendation learning simulation framework that can simulate realistic system-induced data heterogeneity and its effect on various tier-aware FL optimizations.

facebookresearch/nocturne: A data-driven, fast driving simulator for multi-agent coordination under partial observability.

facebookresearch/secure-paper-bidding: Code repo for the ICML 2021 paper "Making Paper Reviewing Robust to Bid Manipulation Attacks".

facebookresearch/KeypointNeRF: KeypointNeRF Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints

facebookresearch/myosuite: MyoSuite is a collection of environments/tasks to be solved by musculoskeletal models simulated with the MuJoCo physics engine and wrapped in the OpenAI gym API.

facebookresearch/holotorch: Holotorch is an optimization framework for differentiable wave-propagation written in PyTorch

facebookresearch/Context-Aware-Representation-Crop-Yield-Prediction: Code for ICDM 2020 paper Context-aware Deep Representation Learning for Geo-spatiotemporal Analysis

facebookresearch/sylph-few-shot-detection: Source code for CVPR 2022 paper Sylph A Hypernetwork Framework for Few-shot Object Detection

facebookresearch/noisy_few_shot: Few-shot learning with mislabeled support samples

facebookresearch/NeuralPassthrough: This repository provides source code, trained neural network model and dataset for our NeuralPassthrough work that is published at SIGGRAPH 2022.

facebookresearch/vrs: VRS is a file format optimized to record & playback streams of sensor data, such as images, audio samples, and any other discrete sensors (IMU, temperature, etc), stored in per-device streams of timestamped records.

facebookresearch/tava: Code for the paper "TAVA Template-free Animatable Volumetric Actors".

facebookresearch/nbm-spam: Training and evaluating NBM and SPAM for interpretable machine learning.

facebookresearch/unbiased-teacher-v2: PyTorch code for CVPR 2022 paper Unbiased Teacher v2 Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors

facebookresearch/ELECTRA-Fewshot-Learning: This repository contains the code for paper Prompting ELECTRA Few-Shot Learning with Discriminative Pre-Trained Models.

facebookresearch/meta-ot: Meta Optimal Transport

facebookresearch/omni3d: Code release for "Omni3D A Large Benchmark and Model for 3D Object Detection in the Wild"

facebookresearch/torchdim: Named tensors with first-class dimensions for PyTorch

facebookresearch/irmae: PyTorch implementation of IRMAE https//arxiv.org/abs/2010.00679

facebookresearch/learning-audio-visual-dereverberation: Code for paper Learning Audio-Visual Dereverberation

facebookresearch/FL_partial_personalization: Federated Learning with Partial Model Personalization

facebookresearch/neural-light-fields: This repository contains the code for Learning Neural Light Fields with Ray-Space Embedding Networks.

facebookresearch/optimizers: For optimization algorithm research and development.

facebookresearch/AVAR_2022_RA_Similarity: Repository with supplementary material of the paper "Towards the prediction of perceived room acoustical similarity" published at AES AVAR 2022.

facebookresearch/diffkt: A framework for automatic differentiation in Kotlin

facebookresearch/Aria_data_tools: Aria data tools provide the open-source toolkit in C++ and Python to interact with data from Project Aria

facebookresearch/Large-Scale-VRD: Visual Relationship Detection

facebookresearch/bo_pr: Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization

facebookresearch/cdeets: The codes reproduce the figures and statistics in the paper, "Calibration of P-values for calibration and for deviation of a subpopulation from the full population," by Mark Tygert. The repo also provides the LaTeX and BibTeX sources required for replicating the paper.

facebookresearch/text_characterization_toolkit: A library for computing diverse text characteristics and using them to analyze data sets and models with ease.

facebookresearch/ddr: Decoupling Dynamics and Reward for Transfer Learning

facebookresearch/3detr: Code & Models for 3DETR - an End-to-end transformer model for 3D object detection

facebookresearch/esm: Evolutionary Scale Modeling (esm): Pretrained language models for proteins

facebookresearch/RidgeSketch: A Fast sketching based solver for large scale ridge regression

facebookresearch/LIGHT: LIGHT is a platform for text-situated dialogue research. We're building out a playable game available at https://www.light-rpg.ai/ for interacting with dialogue models in a grounded setting. This repo contains all of the code to get the LIGHT game running, as well as reproducible code for the research projects along the way of getting LIGHT to where it is.

facebookresearch/ketod: KETOD Knowledge-Enriched Task-Oriented Dialogue

facebookresearch/GradientEpisodicMemory: Continuum Learning with GEM: Gradient Episodic Memory

facebookresearch/luckmatters: Understanding Training Dynamics of Deep ReLU Networks

facebookresearch/adaptive-span: Transformer training code for sequential tasks

facebookresearch/fisher_information_loss: This code reproduces the results of the paper, "Measuring Data Leakage in Machine-Learning Models with Fisher Information"

facebookresearch/ResponsibleNLP: Repository for research in the field of Responsible NLP at Meta.

facebookresearch/one_shot_3d_photography: This repository contains the code release for the SIGGRAPH 2020 paper "One Shot 3D Photography"

facebookresearch/VMZ: VMZ: Model Zoo for Video Modeling

facebookresearch/access: Code to reproduce the experiments from the paper.

facebookresearch/ImageNet-Adversarial-Training: ImageNet classifier with state-of-the-art adversarial robustness

facebookresearch/Mephisto: A suite of tools for managing crowdsourcing tasks from the inception through to data packaging for research use.

facebookresearch/colorlessgreenRNNs: Code and data for paper Colorless Green Recurrent Networks Dream Hierarchically

facebookresearch/meshrcnn: code for Mesh R-CNN, ICCV 2019

facebookresearch/PoincareMaps: The need to understand cell developmental processes has spawned a plethora of computational methods for discovering hierarchies from scRNAseq data. However, existing techniques are based on Euclidean geometry which is not an optimal choice for modeling complex cell trajectories with multiple branches. To overcome this fundamental representation issue we propose Poincaré maps, a method harnessing the power of hyperbolic geometry into the realm of single-cell data analysis.

facebookresearch/NeuralDB: Database Reasoning Over Text project for ACL paper

facebookresearch/Neural_3D_Video: The repository for CVPR 2022 Paper "Neural 3D Video Synthesis"

facebookresearch/slbo: Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees

facebookresearch/fbpcs: FBPCS (Facebook Private Computation Solutions) leverages secure multi-party computation (MPC) to output aggregated data without making unencrypted, readable data available to the other party or any third parties. Facebook provides impression & opportunity data, and the advertiser provides conversion / outcome data.

facebookresearch/mixup-cifar10: mixup: Beyond Empirical Risk Minimization

facebookresearch/tkbc: A knowledge base completion method which handles temporal metadata