IBM Granite Vision tops the chart for small models in document understanding
News
Mike Murphy
Computer Vision
Modern computer vision systems have superhuman accuracy when it comes to image recognition and analysis, but they don’t really understand what they see. At IBM Research, we’re designing AI systems with the ability to see the world like we do.
Our work
IBM Granite now has eyes
ResearchKim MartineauIBM’s new benchmark changes monthly to avoid teaching to the test
ResearchKim MartineauEnvironmental analysis made easier with IBM’s Geospatial Studio
NewsKim MartineauWhat is prompt-tuning?
NewsKim MartineauIBM and NASA team up to spur new discoveries about our planet
NewsKim Martineau3 minute read- See more of our work on Computer Vision
Publications
HyRet-Change: A Hybrid Retentive Network for Remote Sensing Change Detection
- Mustansar Fiaz
- Mubashir Noman
- et al.
- 2025
- IGARSS 2025
Learnable Channel Converter for Multi-Spectral Image to RGB Visualization using a Vision-Text Model
- Haoxiang Qiu
- Tomoya Sakai
- et al.
- 2025
- IGARSS 2025
REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark
- Navve Wasserman
- Roi Pony
- et al.
- 2025
- ACL 2025
Granite Vision: A Demo for Efficient Visual Document Understanding
- Pengyuan Li
- Granite Vision Team
- 2025
- CVPR 2025
MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures
- Lucas Morin
- Valery Weber
- et al.
- 2025
- CVPR 2025
VP Lab: a PEFT-Enabled Visual Prompting Laboratory for Semantic Segmentation
- 2025
- CVPR 2025