C-RADIOv4 (Tech Report)
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917220451352576 |
|---|---|
| author | Ranzinger, Mike Heinrich, Greg McCarthy, Collin Kautz, Jan Tao, Andrew Catanzaro, Bryan Molchanov, Pavlo |
| author_facet | Ranzinger, Mike Heinrich, Greg McCarthy, Collin Kautz, Jan Tao, Andrew Catanzaro, Bryan Molchanov, Pavlo |
| contents | By leveraging multi-teacher distillation, agglomerative vision backbones provide a unified student model that retains and improves the distinct capabilities of multiple teachers. In this tech report, we describe the most recent release of the C-RADIO family of models, C-RADIOv4, which builds upon AM-RADIO/RADIOv2.5 in design, offering strong improvements on key downstream tasks at the same computational complexity. We release -SO400M (412M params), and -H (631M) model variants, both trained with an updated set of teachers: SigLIP2, DINOv3, and SAM3. In addition to improvements on core metrics and new capabilities from imitating SAM3, the C-RADIOv4 model family further improves any-resolution support, brings back the ViTDet option for drastically enhanced efficiency at high-resolution, and comes with a permissive license. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_17237 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | C-RADIOv4 (Tech Report) Ranzinger, Mike Heinrich, Greg McCarthy, Collin Kautz, Jan Tao, Andrew Catanzaro, Bryan Molchanov, Pavlo Computer Vision and Pattern Recognition By leveraging multi-teacher distillation, agglomerative vision backbones provide a unified student model that retains and improves the distinct capabilities of multiple teachers. In this tech report, we describe the most recent release of the C-RADIO family of models, C-RADIOv4, which builds upon AM-RADIO/RADIOv2.5 in design, offering strong improvements on key downstream tasks at the same computational complexity. We release -SO400M (412M params), and -H (631M) model variants, both trained with an updated set of teachers: SigLIP2, DINOv3, and SAM3. In addition to improvements on core metrics and new capabilities from imitating SAM3, the C-RADIOv4 model family further improves any-resolution support, brings back the ViTDet option for drastically enhanced efficiency at high-resolution, and comes with a permissive license. |
| title | C-RADIOv4 (Tech Report) |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.17237 |