Show HN: TikTok but for Scientific Papers
Summary
Papel is a new research-focused social platform that leverages AI-powered vector search and on-device RAG to help researchers discover, discuss, and quiz themselves on academic papers. It offers personalized feeds, local AI chat via Apple Intelligence or MLX, and gamified learning features.
View Cached Full Text
Cached at: 05/11/26, 06:56 PM
Similar Articles
Built a tool that maps research gaps from PDFs — beta, would love ML researchers to break it
The author introduces Papira, a beta tool that analyzes uploaded research papers to map coverage and identify gaps in machine learning and NLP subfields.
I built a TikTok data API (NO AUTH) - profiles, videos, comments, search, hashtags, and social graph as clean JSON
The author announces the addition of TikTok support to Scavio AI, an online search API for AI agents that provides structured JSON data for profiles, videos, comments, and social graphs without requiring authentication.
@tom_doerr: Converts research papers into editable diagrams and slides https://github.com/OpenDCAI/Paper2Any…
Paper2Any is an open-source AI tool that converts research papers into editable diagrams, technical roadmaps, and slide decks with support for universal file formats and custom styling.
@omarsar0: Hacker News → LLM Artifact I built the most personalized HN feed. It only tracks topics I do research around based on m…
A researcher built a personalized Hacker News feed powered by LLMs, memory, and proactive agents that tracks only topics relevant to their research interests, eliminating the need for bookmarks.
@wsl8297: Discovered a deep learning paper reading project on GitHub: paper-reading. Author Mu Shen reads classic and new deep learning papers paragraph by paragraph, recorded into video explanations, has been updated for over 3 years. GitHub: https://github.com/mli/paper-reading...
Mu Shen's deep learning paper reading project on GitHub includes in-depth reading videos of major papers such as GPT-4, Llama 3.1, Sora, etc. Each video is about 1 hour, suitable for AI researchers and developers to deeply understand classic papers.