Open source real-time translation app for Android that runs locally

Xray panel supporting multi-protocol multi-user expire day & traffic & IP limit (Vmess, Vless, Trojan, ShadowSocks, Wireguard, Hysteria, Tunnel, Mixed, HTTP, Tun)

​一站式 New-API/Sub2API 等中转站账号管理：余额/用量看板、自动签到、密钥一键使用、价格对比、可用性测试，另提供高级渠道管理 | All-in-one New-API/Sub2API account hub: balance/usage dashboard, auto check-in, one-click keys, price comparison, health che…

Official implement for "DeepScan: A Training-Free Framework for Visually Grounded Reasoning in Large Vision-Language Models"

Gemini Nexus 是一款面向浏览器场景的 AI 助手扩展，集成 Gemini Web、Gemini API 与 OpenAI 兼容接口，支持网页上下文、图像处理、工具调用和 MCP 浏览器控制。

[ICCV2025]Code Release of Harmonizing Visual Representations for Unified Multimodal Understanding and Generation

跨平台剪贴板同步、历史记录管理工具 / Cross-platform cipboard syncing, history management tool

Can be privately deployed, focusing on providing Obsidian users with a seamless, distraction-free note synchronization plugin with real-time sync across multiple platforms, supporting Mac, Windows,…

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

THEORY OF SPACE: a benchmark for evaluating whether foundation models can actively explore under partial observability efficiently to build, update, and exploit globally consistent spatial beliefs.

Hagezi's Lists are converted to MiHomo mrs format.

保护你的浏览器指纹 | Protect Your Browser Fingerprints | Chrome, Edge, Firefox | 扩展 / Extension

Open-source unified multimodal model

The Arcade Learning Environment (ALE) -- a platform for AI research.

A paper list for spatial reasoning

Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders

Magisk and KernelSU modules for Clash/mihomo services.

Smart, snappy, and multilingual AI assistant for your vault.

PyTorch code and models for V-JEPA self-supervised learning from video.

✨✨Latest Advances on Multimodal Large Language Models

Fast and memory-efficient exact attention

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

[ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.

Awesome Unified Multimodal Models

📖 This is a repository for organizing papers, codes, and other resources related to Latent Reasoning.

一个基于 UWP 平台的第三方酷安客户端精简版

Extensive ReVanced builder. Builds both modules and APKs. Updated daily.

Native Multimodal Models are World Learners