Official Implementation for the paper "d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning"

Remasking Discrete Diffusion Models with Inference-Time Scaling

d2: Improved Techinques for Training Reasonoing Diffusion Language Models

[NeurIPS 2025 Spotlight] Implementation of "KLASS: KL-Guided Fast Inference in Masked Diffusion Models"

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models

[ICLR 2025 Oral] Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

Pytorch implementation of common image generation metrics.

Towards Scalable Pre-training of Visual Tokenizers for Generation

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

YaRN: Efficient Context Window Extension of Large Language Models

(CVPR2024) Official implementation of paper: "Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model"

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

[CVPR 2025 Oral] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

Terminal Velocity Matching

BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models

[CVPR 2025 Oral] Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing

[NeurIPS 2025 Oral] Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think

[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

[NeurIPS 2024] Simple and Effective Masked Diffusion Language Model

A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.

[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"

Official Implementation for Diffusion Models Without Classifier-free Guidance

Code for Fast Training of Diffusion Models with Masked Transformers

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.