# C-RADIOv4 (Tech Report)

arXiv: https://arxiv.org/abs/2601.17237 · HTML: https://mlsanity.com/paper/2601.17237/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 18 references that are in the map.
- First posted on arXiv 24 Jan 2026.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [Probing the 3D Awareness of Visual Foundation Models](https://mlsanity.com/paper/2404.08636/) (2024)
- [AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One](https://mlsanity.com/paper/2312.06709/) (2023)
- [Sharpness-Aware Training for Free](https://mlsanity.com/paper/2205.14083/) (2022)
- [Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design](https://mlsanity.com/paper/2305.13035/) (2023)
- [RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models](https://mlsanity.com/paper/2412.07679/) (2024)
- [RayFronts: Open-Set Semantic Ray Frontiers for Online Scene Understanding and Exploration](https://mlsanity.com/paper/2504.06994/) (2025)
- [Improving robustness to corruptions with multiplicative weight perturbations](https://mlsanity.com/paper/2406.16540/) (2024)
- [FeatSharp: Your Vision Model Features, Sharper](https://mlsanity.com/paper/2502.16025/) (2025)

## Built on by (most cited first, 12 of 12)

- [CP-WSP: A Declarative CP-SAT Framework for Configurable Multi-Constraint Workforce Scheduling](https://mlsanity.com/paper/2607.05177/) (2026)
- [ModuSeg: Decoupling Object Discovery and Semantic Retrieval for Training-Free Weakly Supervised Segmentation](https://mlsanity.com/paper/2604.07021/) (2026)
- [ChangeFlow -- Latent Rectified Flow for Change Detection in Remote Sensing](https://mlsanity.com/paper/2605.15375/) (2026)
- [Cross-Domain Generalization Limits of Vision Foundation Models in Facial Deepfake Detection](https://mlsanity.com/paper/2605.24965/) (2026)
- [SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models](https://mlsanity.com/paper/2605.31597/) (2026)
- [Pretraining Multiple Instance Learning Networks with Multi-Teacher Distillation from Pathology Slide Foundation Models](https://mlsanity.com/paper/2607.14703/) (2026)
- [EOVSAM: Efficient Open-Vocabulary Segmentation with SAM 3 in One Pass](https://mlsanity.com/paper/2608.02284/) (2026)
- [Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States](https://mlsanity.com/paper/2609.04196/) (2026)
- [IronViT: Toward Efficient Generalist Visual Representation Learning](https://mlsanity.com/paper/2609.29252/) (2026)
- [Med-RADIO: Reducing All Medical Domains Into One via Multi-Teacher Distillation](https://mlsanity.com/paper/2609.37682/) (2026)
- [Unlocking Fine-Grained Perception in CLIP via Structurally-Aware Latent Masked Modeling](https://mlsanity.com/paper/2610.07689/) (2026)
- [What Visual Representations Do World Action Models Need?](https://mlsanity.com/paper/2610.13024/) (2026)

## Abstract (arXiv)

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.