DeepSeek · OCR & Document
DeepSeek-OCR-2
Advanced OCR system using visual causal flow methodology for human-like text recognition. Converts documents to markdown with layout preservation and streaming output.
Open the source ↗Similar Vision & Image releases
- Unlimited OCR 2
Baidu · Unlimited-horizon OCR · Week 45, 2026
- WeVisOne-VL
WeChat Vision, Tencent · Vision-Language Model · Week 44, 2026
- Ming-Image-0.1-Design
inclusionAI · Design-Focused Image Model · Week 40, 2026
- LightOnOCR-2-1B
LightOn AI · Document OCR · Week 39, 2026
- Unlimited-OCR
Baidu · Long Horizon OCR · Week 37, 2026
- Riddle
Maxime Rivest · OCR & Document · Week 28, 2026
More from DeepSeek
- DeepInfer
DeepSeek · Inference Engine · Week 44, 2026
- DeepSeek-V4.1-Flash-1017
DeepSeek · Open-Weight LLM · Week 44, 2026
- DeepSeek-V4.1-Flash
DeepSeek · Efficient Multimodal MoE · Week 37, 2026
- DeepSeek-V4-Flash-Vision-Exp
DeepSeek · DeepSeek V4 Vision · Week 36, 2026
- DeepSeek V4 Preview
DeepSeek · Reasoning · Week 17, 2026
- Engram
DeepSeek · Reasoning · Week 4, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.