代码库
Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models. TMLR 2025.
Python
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.
Jupyter Notebook
FAIR Chemistry's library of machine learning methods for chemistry
Python
An open source library designed to provide community examples of Joint Embedding Predictive Architectures (JEPAs). It contains code and examples for learning representations from images, video, and action-conditioned video, as well as planning using JEPA-based models.
Python
Language-Agnostic SEntence Representations
Jupyter Notebook
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
Dialogue model that produces empathetic responses when trained on the EmpatheticDialogues dataset.
Python
Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"
Python
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
[CVPR 2026 Oral] VGGT Omega
Python
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
Python
PyTorch code and models for VJEPA2 self-supervised learning from video.
Python
Can Language Models Rebuild Programs From Scratch?
Python
Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation
Python
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Python
artificial-intelligencepythonpytorch
Code for the paper Hybrid Spectrogram and Waveform Source Separation
Python
State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.
Python
Library for Model Based RL
Python
model-based-reinforcement-learningreinforcement-learning
A library for efficient similarity search and clustering of dense vectors.
C++
1K resolution vision transformers pretrained on 1B human images.
Python