Materials of transformers lecture course

A PyTorch implementation of MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis

Diffusion-LM

Official PyTorch Implementation of "Flow Map Distillation Without Data"

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

“FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching” FlowAR employs a simplest scale design and is compatible with any VAE.

Official PyTorch Implementation of "Latent Denoising Makes Good Visual Tokenizers"

(CVPR 2025) Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

PyTorch code and models for the DINOv2 self-supervised learning method.

[NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation

Pytorch implementation of MeanFlow on ImageNet and CIFAR10

Pytorch implementation of MaskGIT: Masked Generative Image Transformer (https://arxiv.org/pdf/2202.04200.pdf)

A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.

Simple data balancing baselines for worst-group-accuracy benchmarks.

Official implementation of GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver

This repo contains the code for 1D tokenizer and generator

PyTorch implementation of MoCo v3 https//arxiv.org/abs/2104.02057

PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Kandinsky 5.0: A family of diffusion models for Video & Image generation

Official PyTorch implementation of [Direct Diffusion Bridge using Data Consistency for Inverse Problems](https://arxiv.org/abs/2305.19809)

🔥 Official impl. of "DetailFlow: 1D Coarse-to-Fine Autoregressive Image Generation via Next-Detail Prediction"

Autoregressive Image Generation with Randomized Parallel Decoding

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

[CVPR 2025 (Oral)] Open implementation of "RandAR"

Official PyTorch implementation of StyleGAN3

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…