Skip to content

@facebookresearch Meta Research

Change the repository type filter

All

    Repositories list

    1.1k repositories

    • ssvp_slt

      Public
      Self-supervised video pretraining for sign language translation.
      Python
      •
      Other
      •5•12•3•1•Updated Dec 29, 2024Dec 29, 2024

    • optimizers

      Public
      For optimization algorithm research and development.
      Python
      •
      Other
      •33•472•2•2•Updated Dec 28, 2024Dec 28, 2024

    • unibench

      Public
      Python Library to evaluate VLM models' robustness across diverse benchmarks
      Jupyter Notebook
      •
      Other
      •12•172•2•0•Updated Dec 28, 2024Dec 28, 2024

    • faiss

      Public
      A library for efficient similarity search and clustering of dense vectors.
      C++
      •
      MIT License
      •3.7k•32k•222•34•Updated Dec 28, 2024Dec 28, 2024

    • fairseq2

      Public
      FAIR Sequence Modeling Toolkit 2
      pythonmachine-learningdeep-learningpytorchartificial-intelligence
      Python
      •
      MIT License
      •89•747•57•20•Updated Dec 27, 2024Dec 27, 2024

    • spdl

      Public
      Scalable and Performant Data Loading
      Python
      •
      BSD 2-Clause "Simplified" License
      •11•196•6•3•Updated Dec 27, 2024Dec 27, 2024

    • ocean

      Public
      Ocean is the in-house framework for Computer Vision (CV) and Augmented Reality (AR) applications at Meta. It is platform independent and is mainly implemented in C/C++.
      C++
      •
      MIT License
      •59•662•6•0•Updated Dec 27, 2024Dec 27, 2024

    • habitat-sim

      Public
      A flexible, high-performance 3D simulator for Embodied AI research.
      simulatoraicomputer-visioncplusplusroboticssim2real
      C++
      •
      MIT License
      •433•2.7k•163•54•Updated Dec 27, 2024Dec 27, 2024

    • LayerSkip

      Public
      Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024
      optimizationtransformersearly-exitllmspeculative-decodinglayer-drop
      Python
      •
      Other
      •18•250•2•0•Updated Dec 27, 2024Dec 27, 2024

    • Pearl

      Public
      A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.
      Jupyter Notebook
      •
      MIT License
      •171•2.7k•15•1•Updated Dec 27, 2024Dec 27, 2024

    • xformers

      Public
      Hackable and optimized Transformers building blocks, supporting a composable construction.
      Python
      •
      Other
      •634•8.8k•288•12•Updated Dec 27, 2024Dec 27, 2024

    • Qinco

      Public
      Residual Quantization with Implicit Neural Codebooks
      Python
      •
      Other
      •2•49•1•0•Updated Dec 27, 2024Dec 27, 2024

    • LeanUniverse

      Public
      LeanUniverse: A Library for Consistent and Scalable Lean4 Dataset Management
      Python
      •
      Other
      •0•2•0•0•Updated Dec 27, 2024Dec 27, 2024

    • habitat-lab

      Public
      A modular high-level library to train embodied AI agents across a variety of tasks and environments.
      pythonsimulatorresearchreinforcement-learningaicomputer-visiondeep-learningroboticsdeep-reinforcement-learningsim2real
      Python
      •
      MIT License
      •501•2.1k•211•120•Updated Dec 26, 2024Dec 26, 2024

    • sam2

      Public
      The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
      Jupyter Notebook
      •
      Apache License 2.0
      •1.3k•13k•255•36•Updated Dec 25, 2024Dec 25, 2024

    • exca

      Public
      Exca - Execution and caching tool for python
      Python
      •
      MIT License
      •1•57•0•2•Updated Dec 24, 2024Dec 24, 2024

    • pytorch3d

      Public
      PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
      Python
      •
      Other
      •1.3k•8.9k•255•26•Updated Dec 24, 2024Dec 24, 2024

    • offline_rl

      Public
      Simple Ingredients for Offline ReinforcementLearning
      Python
      •
      Other
      •1•6•0•0•Updated Dec 23, 2024Dec 23, 2024

    • recipes

      Public
      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 reprodu…
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •37•297•2•4•Updated Dec 23, 2024Dec 23, 2024

    • multimodal

      Public
      TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •144•1.5k•10•21•Updated Dec 23, 2024Dec 23, 2024

    • flow_matching

      Public
      A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
      Python
      •
      Other
      •63•1.6k•2•0•Updated Dec 23, 2024Dec 23, 2024

    • videoseal

      Public
      Open and efficient video watermarking
      videowatermarking
      Jupyter Notebook
      •
      MIT License
      •18•254•6•0•Updated Dec 22, 2024Dec 22, 2024

    • Kats

      Public
      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.
      Python
      •
      MIT License
      •549•5.2k•55•8•Updated Dec 21, 2024Dec 21, 2024

    • maze_navigation_MLMU

      Public
      Maze navigation with MLM-U
      Jupyter Notebook
      •
      Apache License 2.0
      •0•11•0•0•Updated Dec 21, 2024Dec 21, 2024

    • aepsych

      Public
      AEPsych is a tool for adaptive experimentation in psychophysics and perception research, built on top of gpytorch and botorch.
      HTML
      •
      Other
      •44•58•16•17•Updated Dec 20, 2024Dec 20, 2024

    • hot3d

      Public
      HOT3D: An egocentric dataset for 3D hand and object tracking
      Python
      •
      Apache License 2.0
      •13•96•1•0•Updated Dec 20, 2024Dec 20, 2024

    • pyvrs

      Public
      Python interface for https//github.com/facebookresearch/vrs.
      C++
      •
      Apache License 2.0
      •9•26•1•1•Updated Dec 20, 2024Dec 20, 2024

    • EvalGIM

      Public
      🦾 EvalGIM (pronounced as "EvalGym") is an evaluation library for generative image models. It enables easy-to-use, reproducible automatic evaluations of text-to-image models and supports customization with user-defined metrics, datasets, and visualizations.
      Python
      •
      Other
      •1•50•0•0•Updated Dec 20, 2024Dec 20, 2024

    • metamotivo

      Public
      The first behavioral foundation model to control a virtual physics-based humanoid agent for a wide range of whole-body tasks.
      Python
      •
      Other
      •37•466•3•0•Updated Dec 20, 2024Dec 20, 2024

    • BenchMARL

      Public
      A collection of MARL benchmarks based on TorchRL
      benchmarkmachine-learningreinforcement-learningroboticstorchpytorchmulti-agentrlmulti-agent-reinforcement-learningmarl
      Python
      •
      MIT License
      •47•315•5•2•Updated Dec 20, 2024Dec 20, 2024