New Generation

A page-flipping sketchbook of Singapore. One static HTML file: drag to turn the page, drag the magnifier across it.

Mixture-of-experts (MoE) training megakernel for NVL72s

检查第三方AI API是否掺假以及渠道一致|基于llm指纹的AI模型识别

Repo-aware recommendations for skills, agents, MCP servers, and model harnesses. Use your own inventory or the shipped 79,958-node graph with 68,494 skills, 467 agents, 10,790 MCPs, and 207 harnesses.

🐨 Your assistant's home — the memory, keys, code, and automations your AI agent keeps, portable across every MCP host. Built on Cloudflare Workers.

A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing

Code for "SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes", ICML 2026 Spotlight

Public archive index for the DOJ Epstein Files releases (Datasets 1–12), aggregating official downloads, community mirrors, torrent magnets, and integrity verification to ensure long-term accessibility.

A Claude skill that automatically posts personalized, authentic comments in your target communities.

AI agent skill for writing senior-engineer quality code through SOLID principles, TDD, and clean architecture

auto-paper-digest: An automated pipeline that tracks Hugging Face weekly AI papers, downloads PDFs, imports them into NotebookLM, generates video overviews, and archives everything into a searchable weekly digest.

NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process communication and coordination overheads by allowing programmers to perform one-sided communication from within CUDA kernels and on CUDA streams.

✨✨ [ICLR 2026] Think Beyond Images

📚 GPT4o Prompts Dictionary | Curated Collection of AI Image Generation Prompts

fufufafa dan kearifan lokal-nya

Official implementation of Inductive Moment Matching

A fork of the userscript "Make Bilibili Great Again", but with some experimental features

Monty is a sensorimotor learning framework based on the thousand brains theory of the neocortex.

Implementation of π₀, the robotic foundation model architecture proposed by Physical Intelligence

Comfyui多功能聚合插件（提示词翻译，提示词润色，贴图编辑器，模型引用修复等），让comfyui任意长文本输入框支持中文输入并自动翻译/同时加入报错翻译功能（调用百度翻译），实现翻译自由！同时接入AI大模型实现提示词润色功能， 其它插件功能，请看插件介绍

LDB: A Large Language Model Debugger via Verifying Runtime Execution Step by Step (ACL'24)

电子科技大学信息与软件工程学院学习资料，包含教材、课后答案、实验报告、课程代码、历年真题等，由伏羲主导，多位同学共同参与贡献，欢迎补充、纠错和咨询

[CVPR 2024] SinSR: Diffusion-Based Image Super-Resolution in a Single Step

My chapter-wise notes for Database Internals by Alex Petrov.

Tidal music integration for Subsonic/Jellyfin/Plexamp.

Files important enough for version control

The open source GitBook, Confluence, and Archbee alternative. Write technical docs like never before 🐙

Lightweight Razor-based templates for ASP.NET Core without MVC, Razor Pages, or Blazor.