OpenBMB · OCR & Document
MiniCPM-SALA
Compact multimodal language model optimized for efficient inference with spatial-aware layout analysis capabilities for document understanding and visual reasoning tasks.
Open the source ↗Similar Vision & Image releases
- WeVisOne-VL
WeChat Vision, Tencent · Vision-Language Model · Week 44, 2026
- Unlimited-OCR
Baidu · Long Horizon OCR · Week 37, 2026
- Riddle
Maxime Rivest · OCR & Document · Week 28, 2026
- Granite 4.0 3B Vision
IBM Research · OCR & Document · Week 14, 2026
- GLM-OCR
ZhipuAI · OCR & Document · Week 9, 2026
- DeepSeek-OCR-2
DeepSeek AI · OCR & Document · Week 5, 2026
More from OpenBMB
- MiniCPM5-2B
OpenBMB · Small Reasoning Model · Week 37, 2026
- VoxCPM2
OpenBMB · Tokenizer-Free TTS · Week 36, 2026
- MiniCPM5-1B
OpenBMB · Small Language Models · Week 22, 2026
- MiniCPM-V-4.6
OpenBMB · Visual Understanding · Week 20, 2026
- MiniCPM-o-4.5
OpenBMB · Text Generation · Week 6, 2026
- VoxCPM1.5
OpenBMB · Text-to-Speech · Week 4, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.