A minimalist SOTA LaTeX OCR model with only 20M parameters, running in browser. Full training pipeline available for self-reproduction. | 超轻量SOTA LaTeX公式识
A minimalist SOTA LaTeX OCR model with only 20M parameters, running in browser. Full training pipeline available for self-reproduction. | 超轻量SOTA LaTeX公式识别模型，仅20M参数量，可在浏览器中运行。训练全流程代码开源，以便自学复现。
Maintain this project? Show that it is featured on YunoDB.
[](https://yunodb.com/tools/alephpitexo?utm_source=github&utm_medium=badge)<a href="https://yunodb.com/tools/alephpitexo?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/alephpitexo.svg" alt="Featured on YunoDB" height="20"></a>
🚀 A curated collection of AI engineering resources, roadmaps, tools, and projects covering LLMs, RAG, AI Agents, MCP, fine-tuning, evaluations, and production
Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.
🚀 World's largest GPT Image 2 prompt library, updated daily — 2000+ curated prompts with preview images, 16 languages. OpenAI's next-gen image model with pixel