A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

Character Animation (AnimateAnyone, Face Reenactment)

Foundation Architecture for (M)LLMs

Rotary Transformer

[CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies

MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving

[ICLR 2024 Spotlight] Official implementation of ScaleCrafter for higher-resolution visual generation at inference time.

LVDM: Latent Video Diffusion Models for High-Fidelity Long Video Generation

This repository is an official implementation of ADAPT: Action-aware Driving Caption Transformer, accepted by ICRA 2023.

Let's finetune video generation models!

Rectified Rotary Position Embeddings

[NeurIPS 2022] Pytorch Implementation of SNAKE

[NeurIPS 2022] TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation

[ECCV 2024] TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes

[ICRA 2023] From Semi-supervised to Omni-supervised Room Layout Estimation Using Point Clouds

[ICCV23] DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection

[NeurIPS'22 Spotlight] When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning

The official implementation of "When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning" (ICLR2023)