Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?

[ICCV 2025] The official implementation of MotionLab

The official PyTorch implementation of the paper "Human Motion Diffusion Model"

Official Repository for ICCV 2025 paper DAViD: Modeling Dynamic Affordance of 3D Objects using Pre-trained Video Diffusion Models

Code implementation of the paper 'FIction: 4D Future Interaction Prediction from Video'

Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

[CVPR 2024 Champions][ICLR 2025] Solutions for EgoVis Chanllenges in CVPR 2024

Website source files for Diffusion2GAN Project.

Code release for "EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone" [ICCV, 2023]

The official Meta Llama 3 GitHub site

Official PyTorch implementation of CorrespondentDream: Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondences (CVPR 2024 Poster)

[CVPR'24] Official PyTorch implementation of Contrastive Mean-Shift Learning for Generalized Category Discovery

The suite of modeling video with Mamba

Official PyTorch Implementation of Hypercorrelation Squeeze for Few-Shot Segmentation, ICCV 2021

[CVPR'22] Official PyTorch implementation of Integrative Few-Shot Learning for Classification and Segmentation

Official source code of Fast Point Transformer, CVPR 2022

[CVPR 2022 Oral, Best Paper Finalist] Official PyTorch implementation of FIFO

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.