Meet TeleOCR, a new vision language model that turns any image with text into…
This is a AI post classified by Jev as RAG & memory (a model release), kept by the AI Radar because it carries real work, not commentary.
Meet TeleOCR, a new vision language model that turns any image with text into structured, conversational data. Built on Qwen2.5 VL, it's perfect for document parsing and OCR. With 30k+ downloads, it's already a hit!
Posted by Hugging Models (68.3k followers) 1 h ago · 0 likes · 575 views · view the original post on X. Kept by the AI Radar as RAG & memory.
More AI work like this
- you can find a nice interactive visualization of docjev splitting in action here. — @jerryjliu0
- with jev, everyone is understanding the importance of calibrated confidence scores for… — @jerryjliu0
- Grounded Confidence is here for Extract! 🦙 — @llama_index
- How V7 gives AI agents institutional memory… — @cxocommunity
- 我把「Trader-Archives」做成长期项目了！完全免费开源 — @SUOHA_AI
- 网页截图比文本更适合喂给大模型检索，这个结论我第一眼是不信的。看完伯克利这个团队的 README，觉得他们有道理。 — @GitHub_Daily
- This might be the first open-source memory architecture to cover associative recall. The… — @TencentAI_News
- Wow Jev as a top-k reranker works pretty damn well🤯 — @zainhas
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 40.8k posts from 5k X accounts over the last 14 days, 1.7k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 02:45 UTC. Full method.