Tencent Hunyuan open-sources HyOCR-1.5, a 1B end-to-end OCR large model with 6.37x faster inference
Original title:训推全开源:HyOCR-1.5 让端到端 OCR 大模型跑得更快、看得更准、功能更全
AI summary
Tencent Hunyuan has open-sourced HyOCR-1.5, an end-to-end OCR large model with only 1B parameters that covers more than 8 text-centric tasks and ranks first among end-to-end models on OmniDocBench v1.6 with a score of 94.74.
Key Takeaways
- Tencent Hunyuan has open-sourced HyOCR-1.
- 5,an end-to-end OCR large model with only 1B parameters that covers more than 8 text-centric tasks…
- 6 with a score of 94.
Quick Facts
- Published
- Updated
- Source
- 公众号:腾讯混元
- Category
- Model Releases
- AI score
- 78
轻量端到端OCR的实用化一步,投机解码让长文档生成加速可落地,智能体数据闭环提示了用短板驱动自进化的可复用路径。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Tencent Hunyuan open-sources HyOCR-1.5, a 1B end-to-end OCR large model with 6.37x faster inference. July 13, 2026. https://new.nat6.net/en/news/cmsdu2uhc013profz9af456p4/