Sora research report

An Image is Worth 16x16 Words- Transformers for Image Recognition at Scale

Attention Is All You Need

Auto-Encoding Variational Bayes

Denoising Diffusion Probabilistic Models

Elucidating the Design Space of Diffusion-Based Generative Models

Generating Long Videos of Dynamic Scenes

High-Resolution Image Synthesis with Latent Diffusion Models

Imagen Video- High Definition Video Generation with Diffusion Models

Improved Denoising Diffusion Probabilistic Models

Masked Autoencoders Are Scalable Vision Learners

MoCoGAN- Decomposing Motion and Content for Video Generation

Scalable Diffusion Models with Transformers

Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

SDEdit- Guided Image Synthesis and Editing with Stochastic Differential Equations

ViViT- A Video Vision Transformer

World Models

Adversarial Video Generation on Complex Datasets

Align your Latents- High-Resolution Video Synthesis with Latent Diffusion Models

Deep Unsupervised Learning using Nonequilibrium Thermodynamics

Diffusion Models Beat GANs on Image Synthesis

Generating Videos with Scene Dynamics

Generative Pretraining From Pixels

Hierarchical Text-Conditional Image Generation with CLIP Latents

Improving Image Generation with Better Captions

Language Models are Few-Shot Learners

NÜWA- Visual Synthesis Pre-training for Neural visUal World creAtion

Patch n' Pack- NaViT, a Vision Transformer for any Aspect Ratio and Resolution

Photorealistic Video Generation with Diffusion Models

Recurrent Environment Simulators

Unsupervised Learning of Video Representations using LSTMs

VideoGPT- Video Generation using VQ-VAE and Transformers

Zero-Shot Text-to-Image Generation