New Generation

[ICCV 2025] VistaDream: Sampling multiview consistent images for single-view scene reconstruction

[ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

Astro template to help you build a website for your research paper, based on the Nerfies project page

Full Autonomy Stack for Unitree Go2

A full-stack demo showcasing a local RAG (Retrieval Augmented Generation) pipeline to chat with your PDFs.

An interface automation testing platform based on HttpRunner + Django + Vue + Element UI, production-ready.

A repo to contribute in open source via README only. A dream repo for open source beginner

Unofficial implementation of iTransformer - SOTA Time Series Forecasting using Attention networks, out of Tsinghua / Ant group

A jetpack compose media3 player application

Script that enables audio support on many Chrome devices running various Linux distros

Turn markdown files into structured, queryable data with JS. Build markdown-powered docs, blogs, and sites quickly and reliably.

Build a chatbot or Q&A bot of your website's content

AI based tool to convert vocals lyrics and pitch from music to autogenerate Ultrastar Deluxe, Midi and notes. It automatic tapping, adding text, pitch vocals and creates karaoke files.

learn vim from your terminal with spaced repetition

Use Tailsteam instead of Tailscale!!!

TextOp: Real-time Interactive Text-Driven Humanoid Robot Motion Generation and Control

[ICLR 2026] Taming large-scale few-step training with self-adversarial flows! 👏🏻

An MCP server to query any Postgres database in natural language.

魔改的chromium，指纹浏览器，过掉F12反调试，当前chromium版本140

A book about writing a Chromium fingerprint browser. 免费开源的入门教程，Chromium指纹浏览器开发教程，帮助你了解Chromium内核，并且开发出一套基础的指纹浏览器。

StackRender is the next-gen database schema design and generation tool.

Custom Scratch Runtime made in C++!

A native pdf viewer for Windows and Linux (Wayland/X11) with configurable keybindings.

[CVPR 2025 Oral] OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels

Interesting LLM projects that I created for my YouTube channel using Ollama's open-source models.