Shuyang Gu

Embodied-AI-Guide. [Lumina具身智能社区] 具身智能技术指南 Embodied-AI-Guide

learn-claude-code. Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

ECC. The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

dmvae. [ICML26] Distribution Matching Variational AutoEncoder (DMVAE)

flux2. Official inference repo for FLUX.2 models

RAE. Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

mazegenerator. Generate mazes of different shapes and arbitrary sizes using graph theory

verl. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Bagel. Open-source unified multimodal model

MAGI-1. MAGI-1: Autoregressive Video Generation at Scale

OptimalSteps. Official PyTorch Implementation of "Optimal Stepsize for Diffusion Sampling".

EquivariantModeling. Official PyTorch implementation of the paper "Equivariant Image Modeling"(https://arxiv.org/abs/2503.18948)

TokenSet. Official PyTorch implementation of TokenSet.

dito. Official PyTorch Implementation of "Diffusion Autoencoders are Scalable Image Tokenizers"

star-shaped. Official PyTorch implementation for the paper Star-Shaped Denoising Diffusion Probabilistic Models

vnpy. 基于Python的开源量化交易平台开发框架

1d-tokenizer. This repo contains the code for 1D tokenizer and generator

CCA. Python

dsbm-pytorch. PyTorch Implementation of Diffusion Schrodinger Bridge Matching

scalable-pytorch-sinkhorn. Python

diffusion_schrodinger_bridge. PyTorch Implementation of DSB for Score Based Generative Modeling. Experiments managed using Hydra.

LLM-Agent-Paper-List. The paper list of the 86-page SCIS cover paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

InstructDiffusion. PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.

inst-inpaint. A novel inpainting framework that can remove objects from images based on the instructions given as text prompts.

Kandinsky-2. Kandinsky 2 — multilingual text2image latent diffusion model

MiniGPT-4. Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

Min-SNR-Diffusion-Training. [ICCV 2023] Efficient Diffusion Training via Min-SNR Weighting Strategy

ChatCaptioner. Official Repository of ChatCaptioner

DiT. Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

flash-attention. Fast and memory-efficient exact attention

improved-diffusion. Release for Improved Denoising Diffusion Probabilistic Models

TensoRF. [ECCV 2022] Tensorial Radiance Fields, a novel approach to model and reconstruct radiance fields

rq-vae-transformer. The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)

Awesome-Diffusion-Models. A collection of resources and papers on Diffusion Models

VQ-Diffusion. Python

VQ-Diffusion. Official implementation of VQ-Diffusion

VQ-Diffusion-1. Official implementation of VQ-Diffusion

StyleSwin. [CVPR 2022] StyleSwin: Transformer-based GAN for High-resolution Image Generation

efficient-t2i. Official implementation of the paper Efficient Neural Architecture for Text-to-Image Synthesis.

guided-diffusion. Python

Diff-DALLE. Python

multinomial_diffusion. Python

clip-guided-diffusion. A CLI tool/python module for generating images from text using guided diffusion and CLIP from OpenAI.

LS3DConv. Code of "Learnable Sampling 3D Convolution for Video Enhancement and Action Recognition"

LeetCodeAnimation. Demonstrate all the questions on LeetCode in the form of animation.（用动画的形式呈现解LeetCode题目的思路,完整单步/回看/变速/语音讲解在 algomooc.com）

leetcode-master. 《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

MOGAN. Python

leetcode. LeetCode Solutions: A Record of My Problem Solving Journey.( leetcode题解，记录自己的leetcode解题之路。)

How-To-Ask-Questions-The-Smart-Way. 本文原文由知名 Hacker Eric S. Raymond 所撰寫，教你如何正確的提出技術問題並獲得你滿意的答案。

fieldofjunctions. Implementation of paper: Field of Junctions

ImageNet-Sketch. ImageNet-Sketch data set for evaluating model's ability in learning (out-of-domain) semantics at ImageNet scale

awesome-pretrained-stylegan2. A collection of pre-trained StyleGAN 2 models to download

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

compare_gan. Compare GAN code.

GIQA. Pytorch implementation of Generated Image Quality Assessment

improved_wgan_training. Code for reproducing experiments in "Improved Training of Wasserstein GANs"

wgan-gp. A pytorch implementation of Paper "Improved Training of Wasserstein GANs"

tf.gans-comparison. Implementations of (theoretical) generative adversarial networks and comparison without cherry-picking

style-based-gan-pytorch. Implementation A Style-Based Generator Architecture for Generative Adversarial Networks in PyTorch

Image-Quality-Assessment-Benchmark. A collection of state-of-the-art image quality assessment algorithms

generative_models. Generative Modelling Experiments

pyro. Deep universal probabilistic programming with Python and PyTorch

gmm-torch. Gaussian mixture models in PyTorch.

Relabeled-HELEN-Dataset. rectified version of the original HELEN dataset.

roi-tanh. Face Parsing with RoI Tanh-Warping

pytorch-resnet3d. I3D Nonlocal ResNets in Pytorch

kinetics_i3d_pytorch. Inflated i3d network with inception backbone, weights transfered from tensorflow

kinetics-i3d. Convolutional neural network model for video classification trained on the Kinetics dataset.

ViP. Video Platform for Action Recognition and Object Detection in Pytorch

toflow. TOFlow: Video Enhancement with Task-Oriented Flow

Deformable-Convolution-V2-PyTorch. Deformable ConvNets V2 (DCNv2) in PyTorch

pytorch-OpCounter. Count the MACs / FLOPs of your PyTorch model.

Mask_Guided_Portrait_Editing. pytorch implementation of "Mask-Guided Portrait Editing with Conditional GANs"

pytorch-ssim. pytorch structural similarity (SSIM) loss

Style-Feature-Reshuffle. caffe implementation of "Arbitrary Style Transfer with Deep Feature Reshuffle"

seg2vid. Pytorch implementation of "Video Generation from Single Semantic Label Map", CVPR 2019

vid2vid. Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

object_level_visual_reasoning. Pytorch Implementation of "Object level Visual Reasoning in Videos", F. Baradel, N. Neverova, C. Wolf, J. Mille, G. Mori , ECCV 2018

deep-learning-model-convertor. The convertor/conversion of deep learning models for different deep learning frameworks/softwares.

nlp_course. YSDA course in Natural Language Processing

itwmm. In The Wild 3D Morphable Models

3DDFA. The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.

PyTorch-GAN. PyTorch implementations of Generative Adversarial Networks.

nitrain. Train AI models efficiently on medical images using any framework

Style-Feature-Reshuffle. caffe implementation of "Arbitrary Style Transfer with Deep Feature Reshuffle"

shadowsocks. Python