Publiczne ślady GitHub Meta Research

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.

A library for efficient similarity search and clustering of dense vectors.

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Library for fast text representation and classification.

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

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.

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.

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

PyTorch code and models for the DINOv2 self-supervised learning method.

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

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Foundational Models for State-of-the-Art Speech and Text Translation

Reference PyTorch implementation and models for DINOv3

Hackable and optimized Transformers building blocks, supporting a composable construction.

Code for the paper Hybrid Spectrogram and Waveform Source Separation

Implementation of Nougat Neural Optical Understanding for Academic Documents

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

SAM 3D Objects

Code release for ConvNeXt model

High-resolution models for human tasks.

CoTracker is a model for tracking any point (pixel) on a video.

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.

PyTorch code and models for VJEPA2 self-supervised learning from video.

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

[CVPR 2026 Oral] VGGT Omega

A Python toolbox for performing gradient-free optimization

PyTorch code and models for V-JEPA self-supervised learning from video.

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

An implementation of a deep learning recommendation model (DLRM)

Efficient 3D human pose estimation in video using 2D keypoint trajectories

A flexible, high-performance 3D simulator for Embodied AI research.

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the model.

This repository contains the code to train and evaluate TRIBE v2, a multimodal model for brain response prediction

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

Code and dataset for photorealistic Codec Avatars driven from audio

Self-referential self-improving agents that can optimize for any computable task

State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!

Large Concept Models: Language modeling in a sentence representation space

FAIR Chemistry's library of machine learning methods for chemistry

Non-invasive decoding of typed sentences from MEG and EEG brain recordings using a convolutional encoder, transformer, and character-level language model.

1K resolution vision transformers pretrained on 1B human images.

[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"

Can Language Models Rebuild Programs From Scratch?

Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".

Code for the ShapeR research paper

Momentum Human Rig is an anatomically-inspired parametric full-body digital human model developed at Meta. It includes: A parametric body skeletal model; A realistic 3D mesh skinned to the skeleton with levels of detail;A body blendshape and pose corrective model; A facial blendshape model.Its design is friendly for both CG and CV communities.

projectaria_tools is an C++/Python open-source toolkit to interact with Project Aria data.

Unified automatic quality assessment for speech, music, and sound.

Official repository for "Context Language Models"

SuperDex brings together a purpose-built physics engine, robotics authoring tools, and a scalable reinforcement learning interface in a unified simulation platform, with VR-based teleoperation and additional capabilities planned for future releases.

Efficient Universal Perception Encoder: a single on-device vision encoder with versatile representations that match or exceed specialized experts across multiple task domains.

BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.

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

Pippo: High-Resolution Multi-View Humans from a Single Image

A general physic-based retargeting framework.

Dr. Zero Self-Evolving Search Agents without Training Data

Repository for the CVPR 2026 paper MeshFlow Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer by Weiyu Li, Antoine Toisoul, Tom Monnier, Roman Shapovalov, Rakesh Ranjan, Ping Tan and Andrea Vedaldi.

[CVPR 2026] Pixio: a capable vision encoder dedicated to dense prediction, simply by pixel reconstruction

🎬ActionMesh: A fast video to animated mesh model with unprecedented quality. Generate animated mesh seamlessly importable into any 3D software in less than a minute.

A library for human kinematic motion and numerical optimization solvers to apply human motion

Foundation Models and Data for Human-Human and Human-AI interactions.

Scalable and Performant Data Loading

A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).

[ICLR 2026 Oral (top 1.2%)] Official implementation of DepthLM

Python suite for neuroscience research across all modalities.

ATLAS Autoformalized Textbook Library At Scale

This repo contains the code for the paper "Intuitive physics understanding emerges fromself-supervised pretraining on natural videos"

DACVAE

Expressive Anechoic Recordings of Speech (EARS)

How many bugs can LMs find & fix in large codebases?

Exca - Execution and caching tool for python

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.

Autoform Bot

LSRM is a SOTA, feed-forward 3D reconstruction model that generates high-fidelity, relightable 3D digital twins from sparse 2D views.

An open source environment for digital agents.

Memory Optimizations for Deep Learning (ICML 2023)

Generative Reconstruction with Test-Time Input Alignment

This repository contains utilities for loading data from Meta's datasets with hand pose annotations, computing hand tracking metrics, and visualising results of a hand tracking method.

[NeurIPS 2025] AutoPartGen: Autoregressive 3D Part Generation and Discovery. This is a re-implementation of original model.

Real Acoustic Fields An Audio-Visual Room Acoustics Dataset and Benchmark

Segment This Thing is an efficient image segmentation models that uses a biologically-inspired foveated tokenization to reduce inference costs.

OSS of roboJEPA

PAHF Personalized Agent from Human Feedback

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

Implementation of the NeuroMorph method from CVPR 2021.

This repositories contains the reference implementation for the Sparse Delta Memory paper.More precisely, it contains the model definition as well as triton and cuda kernels for the Sparse Delta Memory layer.

symbolic regression

Automatic textbook formalization of Grinberg Algebraic Combinatorics

The repository provides code for running STyMo Fast and Controllable Few-Shot Motion Style Transfer.

A benchmark with locally sourced multilingual questions for 31 languages.

A Lean Formalization Benchmark for Advanced Mathematics

E2E-SWE Benchmarking LLMs on Building Working Codebases from Scratch

This is the repo of our Memory Driven Proactive Agent

This is the official repo for paper InteractiveWorld A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants

Official implementation of "Learning to Program Retrievals Composing Search Primitives via Reinforcement Learning"