Yihong

jvp_flash_attention. Flash Attention Triton kernel with support for second-order derivatives

i1. Code release for "i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models"

minit2i-torch. Official PyTorch re-implementation of MiniT2I.

UniRL. UniRL is a Framework for Unified Multimodal Model Reinforcement Learning

LongAlign. The official PyTorch implementation for Improving Long-Text Alignment for Text-to-Image Diffusion Models (LongAlign)

Flow-Factory. A unified framework for easy reinforcement learning in Flow-Matching models

DiscAR. Python

ViewFusion. Python

TDM-R1. [ICML 2026][Ultra Powerful Few-Step Diffusion RL] TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward

DGPO. [ICLR 2026][Ultra Fast&Powerful Diffusion RL] Reinforcing Diffusion Models by Direct Group Preference Optimization

starVLA. StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

DeGEM. [ICLR'25] Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs

Reward-Instruct. [NeurIPS 2025] Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation

YOSO. [ICLR 2025] You Only Sample Once: Taming One-Step Text-To-Image Synthesis by Self-Cooperative Diffusion GANs

TDM. [ICCV 2025][Few-Step Student Surpasses Teacher Diffusion] Learning Few-Step Diffusion Models by Trajectory Distribution Matching

yangzhch6.github.io. homepage

FGSAM_NeurIPS24. [NeurIPS'24] Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification

graph-based-deep-learning-literature. links to conference publications in graph-based deep learning

LLM4Graph.

stylegan2-pytorch. Implementation of Analyzing and Improving the Image Quality of StyleGAN (StyleGAN 2) in PyTorch

pytorch-cifar. 95.47% on CIFAR10 with PyTorch

PixArt-sigma. PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

sdxs. SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions

LSGNN. [IJCAI'23] LSGNN: Towards General Graph Neural Network in Node Classification by Local Similarity

dgl. Python package built to ease deep learning on graph, on top of existing DL frameworks.

paper-reading. 深度学习经典、新论文逐段精读

pylinprog. Pure Python implementation of Simplex Method for Linear Programming problem

pytorch_image_classification. PyTorch implementation of image classification models for CIFAR-10/CIFAR-100/MNIST/FashionMNIST/Kuzushiji-MNIST/ImageNet

pytorch-playground. Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)