Pinned Repositories
AnimatedDrawings
Code to accompany "A Method for Animating Children's Drawings of the Human Figure"
audiocraft
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
Detectron
FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
detectron2
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
detr
End-to-End Object Detection with Transformers
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
faiss
A library for efficient similarity search and clustering of dense vectors.
fastText
Library for fast text representation and classification.
sam2
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.
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Meta Research's Repositories
facebookresearch/AnimatedDrawings
Code to accompany "A Method for Animating Children's Drawings of the Human Figure"
facebookresearch/hydra
Hydra is a framework for elegantly configuring complex applications
facebookresearch/mmf
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
facebookresearch/lingua
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
facebookresearch/nevergrad
A Python toolbox for performing gradient-free optimization
facebookresearch/habitat-lab
A modular high-level library to train embodied AI agents across a variety of tasks and environments.
facebookresearch/blt
Code for BLT research paper
facebookresearch/multimodal
TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.
facebookresearch/fairseq2
FAIR Sequence Modeling Toolkit 2
facebookresearch/watermark-anything
Official implementation of the paper "Watermark Anything with Localized Messages"
facebookresearch/fast3r
[CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
facebookresearch/projectaria_tools
projectaria_tools is an C++/Python open-source toolkit to interact with Project Aria data
facebookresearch/audiobox-aesthetics
Unified automatic quality assessment for speech, music, and sound.
facebookresearch/MLGym
MLGym A New Framework and Benchmark for Advancing AI Research Agents
facebookresearch/mvdust3r
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/
facebookresearch/pippo
Pippo: High-Resolution Multi-View Humans from a Single Image
facebookresearch/optimizers
For optimization algorithm research and development.
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/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/spdl
Scalable and Performant Data Loading
facebookresearch/sonata
[CVPR'25Â Highlight] Official repository of Sonata: Self-Supervised Learning of Reliable Point Representations
facebookresearch/momentum
A library for human kinematic motion and numerical optimization solvers to apply human motion
facebookresearch/exca
Exca - Execution and caching tool for python
facebookresearch/SecAlign
Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"
facebookresearch/aepsych
AEPsych is a tool for adaptive experimentation in psychophysics and perception research, built on top of gpytorch and botorch.
facebookresearch/univlg
Unifying 2D and 3D Vision-Language Understanding
facebookresearch/pyvrs
Python interface for https//github.com/facebookresearch/vrs.
facebookresearch/polymath
AI Agent leveraging symbolic reasoning and other auxiliary tools to boost its capabilities on various logic and reasoning benchmarks. This project aims to develop a robust and flexible AI system that can tackle complex problems in areas such as decision-making, mathematics, and programming.
facebookresearch/mowst-gnn
[ICLR 2024] heterogeneous MoE: mixture of weak & strong experts on graphs https//openreview.net/pdf?id=wYvuY60SdD
facebookresearch/gni
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.