Lists (3)
Stars
白霜拼音：蒹葭苍苍，白露为霜。白霜拼音使用高质量语料，进行分词，重新统计字频、词频，归一化，打造纯净、词频准确、智能的词库。白霜词库是目前rime方案下最好的开源词库，经评测准确性已经不输于商业输入法。在墨奇输入法内置，欢迎使用。
A curated list of Rime IME schemata and configs | Rime 輸入方案和配置列表
长任务陪伴器 · 手机监控服务器训练/爬虫/长脚本,端到端加密自托管 · Phone monitoring for long-running server jobs, E2EE & self-hosted
Switch agents. Keep the memory. Local-first search across your AI coding sessions.
AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and supp…
[CVPR 2026] EarlyTom: Early Token Compression Completes Fast Video Understanding
One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks
SGLang is a high-performance serving framework for large language models and multimodal models.
A flexible and efficient codebase for training visually-conditioned language models (VLMs)
[CVPR 2026] Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video Understanding
Logic-in-frames: Dynamic keyframe search via visual semantic-logical verification for long video understanding
💻 vibe coding 2026 | Your First Modern Coding Course Beginners to Master Step by Step.
一个用于在 macOS 上平滑你的鼠标滚动效果或单独设置滚动方向的小工具, 让你的滚轮爽如触控板 | A lightweight tool used to smooth scrolling and set scroll direction independently for your mouse on macOS
[CVPR2025] BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding
A sleek and modern Obsidian theme for desktop and mobile.
An Obsidian plugin that embeds Claude Code/Codex as an AI collaborator in your vault
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Convert your ChatGPT export (ZIP) into clean Markdown text files with inline media, and generate data visualizations like word clouds and usage graphs.
PowerPoint LaTeX 公式转换插件 - Convert LaTeX equations in PowerPoint presentations
🚀 Efficient implementations for emerging model architectures
A paper list of some recent works about Token Compress for Vit and VLM
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Convert Markdown into beautifully styled vertical cards for Xiaohongshu (RED). Automatic paragraph-based pagination, custom themes, and high-quality image export. \n 将 Markdown 文本转化为小红书风格的精美竖版卡片。 支…
Madopic (Markdown to Picture) 精美的 Markdown 转图片/海报工具。让你的知识更有画面感！