Digital PDFs or warped phone photos, TeleOCR parses them with one lightweight 1.2B…
This is a dev post classified by Jev as Other (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Digital PDFs or warped phone photos, TeleOCR parses them with one lightweight 1.2B vision-language model. 📜 Apache 2.0 License. 🤖 https://modelscope.ai/models/XingChen-AGI/TeleOCR 📃 https://modelscope.ai/papers/2608.12898 🏆 Scores 96.87 overall on OmniDocBench v1.6, the highest among the listed specialized VLMs, and ranks #1 in the ICDAR 2026 Sci-ImageMiner Challenge. 📷 Handles digital, photographed, curved, and degraded documents directly, without a separate dewarping model. 🧠 Combines geometry-aware synthesis, consensus-generated labels, image-based self-verification, and progressive traini
Posted by ModelScope (15.9k followers) 2 h ago · 20 likes · 933 views · view the original post on X. Kept by the Dev Radar as Other. Tools mentioned: Ling-3.0-flash-Fin.
More dev work like this
- 🚨重磅！Qwen 正式发布 Qwen Intelligence，个人智能真正走进手机！ — @NFT_Chen
- 得益于中国强大的产业链，MFI认证芯片只需要2块多钱，高大上的 #carplay… — @eastwoodnet
- One generation of SETS Machine. 4.8 seconds. Here's what you're watching 👇 — @Shelpid_WI3M
- SETS Machine is now open source: a self-evolving trading system with genetic strategy… — @Shelpid_WI3M
- 🤖 Great to meet robotics builders at our Embodied Intelligence Workshop at RoseLab,… — @seeedstudio
- Track: Lending & Borrowing ✅ — @xrpl_commons
- 🛠 New Omniston integration example: TON → EVM in a Telegram Mini App — @ston_fi
- HuggingFace now hosts 1,000+ robotics “food” (datasets).🤗 — @CyberRobooo
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. 22.4k posts from 5k X accounts over the last 21 days, 2.6k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 12:49 UTC. Full method.