← Library

1. LFM2.5-230M: Built to Run Anywhere

   Liquid AI · Liquid AI

   Meet LFM2.5-230M, Liquid AI’s smallest model yet: a fast, open-weight foundation model for fine-tuning, edge deployment, tool use, and data extraction.

2. GitHub - bea4dev/ShojiWM: The most customizable Wayland compositor with TypeScript(tsx).

   GitHub

   The most customizable Wayland compositor with TypeScript(tsx). - bea4dev/ShojiWM

3. Autopsy of a deep learning paper

   Piekniewski's blog

   Introduction I read a lot of deep learning papers, typically a few/week. I’ve read probably several thousands of papers. My general problem with papers in machine learning or deep learning is…

4. Unlimited OCR Works

   [Submitted on 22 Jun 2026] · arXiv.org

   Recently, end-to-end OCR models, exemplified by DeepSeek OCR, have once again thrust OCR into the spotlight. A widely held view is that employing a large language model (LLM) as the decoder allows the model to leverage the prior distribution of language, leading to improved OCR performance. However, the downside is equally evident: as the output sequence lengthens, the accumulated KV cache drives up memory consumption and progressively slows down generation. This stands in stark contrast to huma

5. GitHub - baidu/Unlimited-OCR: Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.

   GitHub

   Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing. - baidu/Unlimited-OCR

6. GitHub - uditgoenka/autoresearch: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.

   GitHub

   Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. - uditgoenka/autoresearch