Zexi Wu

EX-4D. The implementation of Extreme Viewpoint 4D Video Generation

Vista4D. Official code, models, and data for Vista4D: Video Reshooting with 4D Point Clouds (CVPR 2026 Highlight)

iztro. ⭐This is a lightweight kit for generating astrolabes for Zi Wei Dou Shu (The Purple Star Astrology), an ancient Chinese astrology. It allows you to obtain your horoscope and personality analysis. 支持多语言轻量级获取紫微斗数排盘信息的javascript开源库。

EasyVolcap. [SIGGRAPH Asia 2023 (Technical Communications)] EasyVolcap: Accelerating Neural Volumetric Video Research

MoE-GS. Official code of "MoE-GS: Mixture of Experts for Dynamic Gaussian Splatting (ICLR 2026)"

giga-world-1. A Roadmap to Build World Models for Robot Policy Evaluation

MLSLabsGaussianSplattingRenderer-UE. A high-performance Unreal Engine 5 (UE5) plugin developed by MaLanShan Audio & Video Laboratory, designed for real-time visualization, management, and scalable rendering of 3D Gaussian Splatting (3DGS) and dynamic Volumetric Video (4DGS).

Blender-3DGS-4DGS-Viewer-Node. A lightweight point-based visualization tool used for inspecting Gaussian data, designing camera motion, and exporting setups for external Gaussian renderers.

Diff4Splat. [CVPR 2026] Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models.

Flow4DGS-SLAM. Official Implementation of the CVPR 2026 Highlight paper "Flow4DGS-SLAM: Optical Flow-Guided 4D Gaussian Splatting SLAM".

worldmesh. [ECCV 2026] WorldMesh: Generating Navigable Multi-Room 3D Scenes via Mesh-Conditioned Image Diffusion

inspatio-world. Python

world-models. A curated list of research and projects on world models

ProtoMotions. ProtoMotions is a GPU-accelerated simulation and learning framework for training physically simulated digital humans and humanoid robots.

MocapAnything. [SIGGRAPH ASIA 2026]: End-to-End Motion Capture for Arbitrary Skeletons

amass. Data preparation and loader for AMASS

Agentic-RL-Most-Detailed-Intro. Agentic RL最详细入门

TripoSplat. TripoSplat converts a single 2D image into high-quality and variable number of 3D Gaussians, developed by TripoAI.

meshy-3d-agent. Build Meshy 3D agent skills to generate, texture, rig, animate, and prep 3D models for print without an MCP server

movie-script-scraper. A simple scrapper to retrieve scripts by genre or title from IMSDB.

Kiln. Describe it or draw it — Kiln makes it real. The open-source MCP server for 3D printing: AI agents (Claude, Codex, Cursor, or any MCP client) design, generate, slice & print on Bambu Lab, Creality, Prusa, Elegoo, Klipper/Moonraker, OctoPrint, Duet/RepRapFirmware & any Marlin printer.

Light-X. [ICLR 2026] Light-X: Generative 4D Video Rendering with Camera and Illumination Control

SceneConductor. SceneConductor: 3D Scene Generation from a Single Image with Multi-Agent Orchestration

AwesomeOPD. Awesome List for On-Policy Distillation

TRELLIS.2. Native and Compact Structured Latents for 3D Generation

cutscene_agent. An LLM Agent Framework for Automated 3D Cutscene Generation.

claude-code-analysis. 🤖 The analysis of Claude Code

OpenMontage. World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.

LatentSpatialMemory. Latent Spatial Memory for Video World Models

DreamX-World. DreamX-World: A General-Purpose Interactive World Model

mujoco_menagerie. A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.

SwiftVR. Repo for SwiftVR: Real-Time One-Step Generative Video Restoration

CloakBrowser. Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 30/30 tests passed.

CollectionLoRA. [ECCV 2026] Implementation of "CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation"

minWM. A Minimal and Elegant Framework & Tutorial for Real-Time Interactive World Models

OpenWorldLib. Unified Codebase for Advanced World Models.

Awesome-Robotics-Manipulation. A comprehensive list of papers about Robot Manipulation, including papers, codes, and related websites.

MovieHub. 电影片源自动抓取：智能抓取引擎，从网络上发现高质量的影片发布（4K、HDR、杜比视界）

figures4papers. My Python scripts to make high-quality figures for publications in top AI conferences and journals.

awesome-opds. A list of awesome resources for OPDS users and developers

G-OPD. Official repository for the paper "Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation"

Video2LoRA. Video2LoRA: Unified Semantic-Controlled Video Generation via Per-Reference-Video LoRA （CVPR 2026 Findings）

HY-World-2.0. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

FlashVSR. [CVPR 2026] Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny conditional decoder.

ViFeEdit. [Preprint] ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer

worldfm. Python

HGP-Mamba. Official Code for "HGP-Mamba: Integrating Histology and Generated Protein Features for Mamba-based Multimodal Survival Risk Prediction"

Awesome-Autoregressive-Video-Diffusion. Collection of forcing related autoregressive video Gen

Awesome-Video-Diffusion. A curated list of recent diffusion models for video generation, editing, and various other applications.

Causal-Forcing. [ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++

ResumeSample. Resume template for Chinese programmers . 程序员简历模板系列。包括PHP程序员简历模板、iOS程序员简历模板、Android程序员简历模板、Web前端程序员简历模板、Java程序员简历模板、C/C++程序员简历模板、NodeJS程序员简历模板、架构师简历模板以及通用程序员简历模板

Awesome-World-Models. A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, Embodied AI, and Autonomous Driving, including papers, codes, and related websites.

lingbot-world. Advancing Open-source World Models

diffusers-torchao. End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).

HuggingfaceProxy. 本项目主要是用来解决国内无法直接下载 Hugging Face 模型和数据集的问题。通过 Cloudflare Workers 搭建的镜像代理，提供稳定快速的访问服务，让你能够无缝获取 Hugging Face 的资源。This project provides a stable and fast proxy service, allowing you to access Hugging Face resources seamlessly.

awesome-llm-based-agent4code.

LLMAgentPapers. Must-read Papers on LLM Agents.

personal-site. My personal website - built with Next for Static-Export, and GitHub Pages.

academic-project-page-template-vue. A vue-based project page template for academic papers. (in development) https://junyaohu.github.io/academic-project-page-template-vue

kit. 🧱 Describe your site, AI builds it, you own it as Markdown. Snap together Tailwind blocks like Lego — landing pages, blogs, portfolios, docs & more. No AI slop. Free to deploy anywhere 👇

readme-typing-svg. ⚡ Dynamically generated, customizable SVG that gives the appearance of typing and deleting text for use on your profile page, repositories, or website.

profileme-dev. Create an awesome GitHub profile in minutes

beautify-github-profile. This repository will assist you in creating a more beautiful and appealing github profile, and you will have access to a comprehensive range of tools and tutorials for beautifying your github profile. 🪄 ⭐

DenverCoder1. Jonah Lawrence's Profile README

awesome-github-profile-readme. 😎 A curated list of awesome GitHub Profile which updates in real time

buildawesome. A simpler site generator. Transforms a directory of templates (of varying types) into HTML.

al-folio. A beautiful, simple, clean, and responsive Jekyll theme for academics

HyperDreamBooth.

HuggingFace-Download-Accelerator. 利用HuggingFace的官方下载工具从镜像网站进行高速下载。

HyperDreamBooth. Python

HyperKohaku. A diffusers based implementation of HyperDreamBooth

BayesDiff. Python

diffusion-posterior-sampling. Official pytorch repository for "Diffusion Posterior Sampling for General Noisy Inverse Problems"

FramePack. Lets make video diffusion practical!

awesome-ocr.

VBench. [CVPR2024 Highlight] VBench - We Evaluate Video Generation

awesome-video-generation. A collection of awesome video generation studies.

Restormer. [CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.

All-in-One-Image-Restoration-Survey. [IEEE TPAMI 2025] A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends

Awesome-CVPR2026-CVPR2025-CVPR2024-CVPR2021-CVPR2020-Low-Level-Vision. A Collection of Papers and Codes for CVPR2026/CVPR2025/CVPR2024/CVPR2021/CVPR2020 Low Level Vision

CodeFormer. [NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

IPC-Dehaze. [CVPR2025] Iterative Predictor-Critic Code Decoding for Real-World Image Dehazing

AdaptiveSupervisedPatchNCE. Python

UNI. Pathology Foundation Model - Nature Medicine

ImageFolder. High-performance Image Tokenizers for VAR and AR

ControlVAR. This is the official implementation for ControlVAR.

cursor-auto-free. auto sign cursor

StainPromptInversion. Official implementation of AAAI25 "Unpaired Multi-Domain Histopathology Virtual Staining using Dual Path Prompted Inversion"

OSASIS. Python

Image-Super-Resolution-via-Iterative-Refinement. Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch

Palette-Image-to-Image-Diffusion-Models. Unofficial implementation of Palette: Image-to-Image Diffusion Models by Pytorch

DDBM. Python

latent-diffusion. High-Resolution Image Synthesis with Latent Diffusion Models

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

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

StyTR-2. StyTr2 : Image Style Transfer with Transformers

PITI. PITI: Pretraining is All You Need for Image-to-Image Translation

cycle-diffusion. [ICCV 2023] A latent space for stochastic diffusion models

stable-diffusion. A latent text-to-image diffusion model

stylegan3. Official PyTorch implementation of StyleGAN3

StyleID. [CVPR 2024 Highlight] Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer

INR-st. Official repository for Controllable Style Transfer via Test-time Training of Implicit Neural Representation

AttentionGAN. AttentionGAN for Unpaired Image-to-Image Translation & Multi-Domain Image-to-Image Translation

VisualThinker-R1-Zero. Explore the Multimodal “Aha Moment” on 2B Model

guided-diffusion. Python

DDPG. Python

Fast-DDPM. Python

Awesome-Diffusion-Models-in-Medical-Imaging. Diffusion Models in Medical Imaging (Published in Medical Image Analysis Journal)

ddrm. [NeurIPS 2022] Denoising Diffusion Restoration Models -- Official Code Repository

DDNM. [ICLR 2023 Oral] Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model

awesome-diffusion-models-in-low-level-vision. A Repository for Diffusion-Model-related Papers in Low-level Vision

StyleDiffusion. Python

Puff-Net. Puff-Net

Awesome-Diffusion-for-Image-Translation. A collection of papers on Diffusion for Image-to-Image Translation and Style Transfer

Conditional-Consistency-Models. This repository contains the official implementation and supplementary materials for the research paper "Conditional Consistency Guided Image Translation and Enhancement". It explores advanced consistency models for conditional data generation, focusing on tasks like low-light enhancement and infrared-to-visible translation.

peS2o. Pretraining Efficiently on S2ORC!

R1-V. Witness the aha moment of VLM with less than $3.

Logic-RL. Reproduce R1 Zero on Logic Puzzle

open-r1. Fully open reproduction of DeepSeek-R1

TinyZero. Minimal reproduction of DeepSeek R1-Zero

retrieval-scaling. Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".

PSPStain. [MICCAI 2024]Official implementation of "Pathological Semantics-Preserving Learning for H&E-to-IHC Virtual Staining"

LLaVA-CoT. [ICCV 2025] LLaVA-CoT, a visual language model capable of spontaneous, systematic reasoning

LlamaV-o1. [ACL 2025 🔥] Rethinking Step-by-step Visual Reasoning in LLMs

visioStencils. 4,486 visio :art: shapes, stencils, symbols, and icons collection to visually represent your IT infrastructure

AgentLaboratory. Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

PromptCBLUE--Jarvis-XJTU. The code share of our team (Jarvis-XJTU) in the CCKS2023 PromptCBLUE competition.

Randeng-MLT-PromptCBLUE. CCKS2023-PromptCBLUE: Code implement of TianChi completition

cnkiSpyder. 中国知网Selenium爬虫

CNKI-PDF-RIS-Helper. 油猴知网PDF+RIS下载助手、油猴SCI RIS下载助手

CNKI-download. :frog: 知网(CNKI)文献下载及文献速览爬虫 (Web Scraper for Extracting Data)

cnki_patent_scrapy. Python

CNKI_VIEW. selenium/requests 知网爬虫以及附带图像界面的爬虫结果(表格)查看器 / a GUI viewer of crawl results of cnki with crawler based on selenium/requests and pyqt

cnki-journal-info. A spider to crawl CNKI journal info

batch_download_from_CNKI. 对知网的搜索结果进行自动执行“全选”和“下一页”，最后使用知网研学进行下载（下载下来是es6文件，使用知网研学打开进行PDF文件下载）

tiny-universe. 《大模型白盒子构建指南》：一个全手搓的Tiny-Universe

self-llm. 《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

ABigSurveyOfLLMs. A collection of 150+ surveys on LLMs

useful-computer-vision-phd-resources. Lists of resources useful for my PhD in computer vision

academicpages.github.io. Github Pages template based upon HTML and Markdown for personal, portfolio-based websites.

img2img-turbo. One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more

DoiHunter. A python package that helps the researcher to download the research paper in bulk using a txt file.

python-project-template. This template is **archived**. > UV can now [generate a sample project](https://docs.astral.sh/uv/guides/projects/#creating-a-new-project) > I recommend using **UV** to bootstrap your peojects. > [Copier](https://github.com/copier-org/copier) is a tools that can bootstrap projects from templates.

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

LLM-Paper-Lists. Explanation to key concepts and classical models in LLM and AIGC

Awesome-AGI. AGI资料汇总学习（主要包括LLM和AIGC），持续更新......

fine-tune-train_segment_anything_2_in_60_lines_of_code. The repository provides code for training/fine tune the Meta Segment Anything Model 2 (SAM 2)

WSI-SAM. WSI-SAM

SAM4MIS. Segment Anything Model for Medical Image Segmentation: Open-Source Project Summary

OpenScholar. This repository includes the official implementation of OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs.

CS-PhD-Application-fee-waivers. Collections of CS PhD Application Fee Waivers of schools in North America

Graduate_Application. Documents used for grad school application

awesome-semantic-segmentation. :metal: awesome-semantic-segmentation

Deep-Learning-Image-Segmentation. Deep Learning Image Segmentation: Theory and Practice

Hands-On-Large-Language-Models. Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

learn-nlp-with-transformers. we want to create a repo to illustrate usage of transformers in chinese

DCD-GAN. Unpaired Deep Image Deraining Using Dual Contrastive Learning (CVPR 2022)

DCLGAN. Code for Dual Contrastive Learning for Unsupervised Image-to-Image Translation, NTIRE, CVPRW 2021, oral.

wos-selenium. Web of Science spider implemented with selenium

web-of-science-downloader. Python

pytorch-CycleGAN-and-pix2pix. Image-to-Image Translation in PyTorch

learn_python3_spider. python爬虫教程系列、从0到1学习python爬虫，包括浏览器抓包，手机APP抓包，如 fiddler、mitmproxy，各种爬虫涉及的模块的使用，如：requests、beautifulSoup、selenium、appium、scrapy等，以及IP代理，验证码识别，Mysql，MongoDB数据库的python使用，多线程多进程爬虫的使用，css 爬虫加密逆向破解，JS爬虫逆向，分布式爬虫，爬虫项目实战实例等

wos-download-bot. Wos核心数据集批量下载油猴脚本

zotero-reference. PDF references add-on for Zotero.

eat_pytorch_in_20_days. Pytorch🍊🍉 is delicious, just eat it! 😋😋

GPT_API_free. Free ChatGPT&DeepSeek API Key，免费ChatGPT&DeepSeek API。免费接入DeepSeek API和GPT4 API，支持 gpt | deepseek | claude | gemini | grok 等排名靠前的常用大模型。

PaperDownloader. 使用 selenium 完成知网/万方数据库论文批量下载

zotero-style. Ethereal Style for Zotero

PlotNeuralNet. Latex code for making neural networks diagrams

jekyllthemes. A directory of the best-looking themes for Jekyll blogs

lectureCode-sp18. lecture code

DLUT_SE_Courses. 大连理工大学软件工程专业课程指南 开发区其他专业见组织内对应仓库

Zhang-Each.github.io_oldpage. My personal page.

PaperWriting.

My-CS-Notebook. My notebook of CS learning.

BiSheServer. 本系统是我的毕业设计项目，题目为“基于用户画像的电影推荐系统的设计与实现”。主要是以Django作为基础框架，采用MTV模式，数据库使用MongoDB、MySQL和Redis，以从豆瓣平台爬取的电影数据作为基础数据源，主要基于用户的基本信息和使用操作记录等行为信息来开发用户标签，并使用Hadoop、Spark大数据组件进行分析和处理的推荐系统。管理系统使用的是Django自带的管理系统，并使用simpleui进行了美化。

air_ticket_book. 软件工程课程设计-旅行社机票预定系统

allProject. 宠物领养小程序、在线教育系统、考试小程序、医院挂号小程序、电影购票小程序、电商书城、酒店预订系统、酒店管理系统、房屋租赁系统、超市管理系统、超市账单、超市收银、人事管理系统、个人博客系统、商城、宠物租赁管理系统、宠物交易管理系统、宠物医院系统、花店商城、网上鲜花、景区旅游系统、电影购票、教务管理系统、宿舍管理、电影票会员、招聘系统、大学生社团系统、民宿预订、校园疫情管理、动漫商城、校园二手交易系统、校园交流论坛、动漫论坛、在线考试、仓库管理系统、心理咨询系统、健身房管理系统、图书管理系统、物资管理系统、小米商城系统、汽车租赁系统、小区物业系统、高校就业、点餐、医院门诊挂号、停车场、蛋糕商城、校园跑腿、外卖、养老院、小说阅读、文物收藏、手机商城、房屋中介、房屋维修、图书馆座位预约、医院hrp

ML_DL_CV_with_pytorch. 一个计算机视觉、机器学习与深度学习相关的项目，看课程的笔记还有自己做的程序

eecs-498-2020. EECS 498/598: Deep Learning for Computer Vision [Fall 2020]

EECS498-008-Deep-Learning-CV. Jupyter Notebook

EECS498-007. Jupyter Notebook

Retinexformer. "Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement" (ICCV 2023 Top-10 Cited 🏆) & (NTIRE 2024 Runner-Up 🏆) & (NTIRE 2025 Winner 🏆) & (NTIRE 2026 Winner 🏆)

mmdetection. OpenMMLab Detection Toolbox and Benchmark

ISINet. Pytorch implementation of the MICCAI 2020 paper ISINet: An Instance-Based Approach for Surgical Instrument Segmentation.

Surgical_instruments. Repo for images, annotations, notebooks and models for detecting surgical instruments.

Surgical_instruments_app. Deployment of model that detects and identifies 15 classes of surgical instruments.

machine-learning-example. Jupyter Notebook

computer-science-in-DLUT-3. 大连理工大学大三计算机系资料

eecs498. Jupyter Notebook

Deep-Learning-Interview-Book. 深度学习面试宝典（含数学、机器学习、深度学习、计算机视觉、自然语言处理和SLAM等方向）

dlut_cv20_project. cv class

computer-science-in-DLUT-2-. 大工计算机系大二学年资料

dlut-cs-courseware. :book: 大连理工计算机课件

SSDUT-learning-materials. 这些是我本科四年的专业课学习资料，分享给大家，也欢迎大家把里面没有的传进去，一定不要造轮子啊。😀

DLUT-library-auto-reservation. 大连理工大学图书馆自动预约座位小程序

dlut-ipv6. 利用ipv6免流蹭网，大连理工都气哭惹

libdlut. 大连理工大学课程攻略共享公益项目

SurviveSCUManual. 《四川大学计软网学生自救手册》