Official repository for our work on micro-budget training of large-scale diffusion models.

More relighting!

Official implementation of ICCV 2023 Oral Paper "Role-Aware Interaction Generation from Textual Description"

Official implementation of AAAI 2023 Oral Paper "Frame-Level Label Refinement for Skeleton-Based Weakly-Supervised Action Recognition"

PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]

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 minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.

Massive open Japanese speech corpus

Official code for "DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps" (Neurips 2022 Oral)

Gaussian-Bernoulli Restricted Boltzmann Machines

Robust Speech Recognition via Large-Scale Weak Supervision

A latent text-to-image diffusion model

Implementation of Bit Diffusion, Hinton's group's attempt at discrete denoising diffusion, in Pytorch

[ICML 2023] Official PyTorch implementation of Global Context Vision Transformers

Release for Improved Denoising Diffusion Probabilistic Models

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

JGLUE: Japanese General Language Understanding Evaluation

Web application for image and video labeling and annotation

A PyTorch-based library for semi-supervised learning (NeurIPS'21)

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

Official PyTorch Implementation for "Rotate to Attend: Convolutional Triplet Attention Module." [WACV 2021]

State-of-the-Art Text Embeddings

Official Implementation of Early-Learning Regularization Prevents Memorization of Noisy Labels

Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.