Skip to content

@facebookresearch Meta Research

Change the repository type filter

All

    Repositories list

    1.1k repositories

    • 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
      •514•2.1k•217•125•Updated Feb 12, 2025Feb 12, 2025

    • aepsych

      Public
      AEPsych is a tool for adaptive experimentation in psychophysics and perception research, built on top of gpytorch and botorch.
      HTML
      •
      Other
      •47•60•16•22•Updated Feb 11, 2025Feb 11, 2025

    • fairseq2

      Public
      FAIR Sequence Modeling Toolkit 2
      pythonmachine-learningdeep-learningpytorchartificial-intelligence
      Python
      •
      MIT License
      •91•787•61•16•Updated Feb 11, 2025Feb 11, 2025

    • blt

      Public
      Code for BLT research paper
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •103•1.4k•18•4•Updated Feb 11, 2025Feb 11, 2025

    • param

      Public
      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.
      Python
      •
      MIT License
      •62•128•10•11•Updated Feb 11, 2025Feb 11, 2025

    • tokentune

      Public
      This repository provides code for the paper "Memory-Efficient Fine-Tuning of Transformers via Token Selection" (EMNLP 2024).
      Python
      •
      Other
      •0•1•0•0•Updated Feb 11, 2025Feb 11, 2025

    • projectaria_tools

      Public
      projectaria_tools is an C++/Python open-source toolkit to interact with Project Aria data
      C++
      •
      Apache License 2.0
      •74•542•12•3•Updated Feb 11, 2025Feb 11, 2025

    • HolisticTraceAnalysis

      Public
      A library to analyze PyTorch traces.
      Python
      •
      MIT License
      •47•327•18•8•Updated Feb 11, 2025Feb 11, 2025

    • partnr-planner

      Public
      A repository accompanying the PARTNR benchmark for using Large Planning Models (LPMs) to solve Human-Robot Collaboration or Robot Instruction Following tasks in the Habitat simulator.
      Python
      •
      MIT License
      •15•184•4•1•Updated Feb 11, 2025Feb 11, 2025

    • BenchMARL

      Public
      A collection of MARL benchmarks based on TorchRL
      benchmarkmachine-learningreinforcement-learningroboticstorchpytorchmulti-agentrlmulti-agent-reinforcement-learningmarl
      Python
      •
      MIT License
      •55•340•8•4•Updated Feb 11, 2025Feb 11, 2025

    • pippo

      Public
      Pippo: High-Resolution Multi-View Humans from a Single Image
      Python
      •
      Other
      •3•31•0•0•Updated Feb 11, 2025Feb 11, 2025

    • xformers

      Public
      Hackable and optimized Transformers building blocks, supporting a composable construction.
      Python
      •
      Other
      •646•9k•296•6•Updated Feb 11, 2025Feb 11, 2025

    • optimizers

      Public
      For optimization algorithm research and development.
      Python
      •
      Other
      •37•490•2•3•Updated Feb 10, 2025Feb 10, 2025

    • habitat-sim

      Public
      A flexible, high-performance 3D simulator for Embodied AI research.
      simulatoraicomputer-visioncplusplusroboticssim2real
      C++
      •
      MIT License
      •446•2.8k•171•53•Updated Feb 10, 2025Feb 10, 2025

    • gni

      Public
      GPU Node ID (gni) is a rust based library for creating a unique identifier for the set of GPUs running on the host. The ID is generated by hashing (blake3) all GPU UUIDs sorted lexicographically.
      Rust
      •
      Apache License 2.0
      •3•2•0•0•Updated Feb 10, 2025Feb 10, 2025

    • generative-recommenders

      Public
      Repository hosting code for "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).
      recommendationsrecsysrecommender-systemsactions-speak-louder-than-wordsgenerative-recommendershstu
      Python
      •
      Apache License 2.0
      •164•886•12•3•Updated Feb 10, 2025Feb 10, 2025

    • minihack

      Public
      MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research
      Python
      •
      Apache License 2.0
      •60•487•8•2•Updated Feb 10, 2025Feb 10, 2025

    • mvdust3r

      Public
      Open source impl of **MV-DUSt3R+ Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds** from Meta Reality Labs. Project page https://mv-dust3rp.github.io/
      Python
      •
      Other
      •10•337•4•1•Updated Feb 10, 2025Feb 10, 2025

    • spdl

      Public
      Scalable and Performant Data Loading
      Python
      •
      BSD 2-Clause "Simplified" License
      •11•215•5•3•Updated Feb 10, 2025Feb 10, 2025

    • 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
      •151•1.5k•10•22•Updated Feb 10, 2025Feb 10, 2025

    • 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
      •36•305•2•4•Updated Feb 10, 2025Feb 10, 2025

    • Aria_data_tools

      Public
      Aria data tools provide the open-source toolkit in C++ and Python to interact with data from Project Aria
      C++
      •
      Apache License 2.0
      •22•110•1•0•Updated Feb 10, 2025Feb 10, 2025

    • LayerSkip

      Public
      Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024
      optimizationtransformersearly-exitllmspeculative-decodinglayer-drop
      Python
      •
      Other
      •22•269•3•1•Updated Feb 9, 2025Feb 9, 2025

    • Pearl

      Public
      A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.
      Jupyter Notebook
      •
      MIT License
      •178•2.8k•13•0•Updated Feb 8, 2025Feb 8, 2025

    • faiss

      Public
      A library for efficient similarity search and clustering of dense vectors.
      C++
      •
      MIT License
      •3.7k•33k•225•35•Updated Feb 8, 2025Feb 8, 2025

    • DRTK

      Public
      Differentiable Rendering Toolkit
      Cuda
      •
      MIT License
      •7•81•4•1•Updated Feb 8, 2025Feb 8, 2025

    • A2B

      Public
      A2B Neural Rendering of Ambisonic Recordings to Binaural
      Python
      •
      Other
      •1•1•0•0•Updated Feb 7, 2025Feb 7, 2025

    • audiobox-aesthetics

      Public
      Unified automatic quality assessment for speech, music, and sound.
      Python
      •
      Creative Commons Attribution 4.0 International
      •3•211•1•0•Updated Feb 7, 2025Feb 7, 2025

    • 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
      •577•5.6k•56•8•Updated Feb 7, 2025Feb 7, 2025

    • hydra

      Public
      Hydra is a framework for elegantly configuring complex applications
      Python
      •
      MIT License
      •660•9k•274•39•Updated Feb 7, 2025Feb 7, 2025