Rad-JEPA 3D: Radiology Joint-Embedding Predictive Model for 3D Computed Tomography
Rad-JEPA 3D is a self-supervised pretraining framework that learns volumetric CT representations by predicting latent features from a masked view. Its core hybrid H-Mamba encoder combines Mamba state-space and grouped-query attention, and Hidden States Orthogonal Regularization (HSOR) improves representation quality. Pretrained on ~120,000 CT scans, it achieves SOTA with only 4.0B parameters on closed-ended VQA and spatial reasoning benchmarks.
-->
[Submitted on 28 Jul 2026]
Title:Rad-JEPA 3D: Radiology Joint-Embedding Predictive Model for 3D Computed Tomography
View a PDF of the paper titled Rad-JEPA 3D: Radiology Joint-Embedding Predictive Model for 3D Computed Tomography, by Quoc-Huy Trinh and 2 other authors
View PDF HTML (experimental)
Abstract:Self-supervised pretraining is central to 3D medical image analysis, where unlabeled CT volumes are abundant but expert annotations are scarce. Yet existing volumetric encoders often fail to preserve the coarse spatial and geometric structure that downstream reasoning depends on, limiting their performance on organ disentanglement, abnormality detection, and spatial understanding when paired with language models. We introduce Rad-JEPA 3D, a joint-embedding predictive framework that learns volumetric CT representations by predicting the latent features of a complete scan from a masked view. At its core is a hybrid H-Mamba encoder that fuses a Mamba state-space branch, which models inter-slice continuity through sequential scanning, with a grouped-query attention branch, which captures cross-plane spatial context, combined through a lightweight per-token router. To improve the quality of intermediate representations, we further propose Hidden States Orthogonal Regularization (HSOR), which aligns student-teacher hidden states and reduces feature redundancy throughout the encoder. This layer-wise regularization produces more consistent and discriminative volumetric representations, leading to improved performance on organ recognition and spatial reasoning tasks. Pretrained on approximately 120,000 CT scans, Rad-JEPA 3D attains state-of-the-art results despite its compact size: with only 4.0B total parameters, it achieves competitive results with state-of-the-art on closed-ended VQA and the best average spatial-reasoning score on the Spatial-Med benchmark. Ablation studies confirm that the hybrid block and HSOR contribute complementary gains, and that the induced spatial structure can substitute for raw language-model scale on volumetric reasoning tasks.
Subjects:
Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:2607.26196 [cs.CV]
(or arXiv:2607.26196v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2607.26196
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Quoc-Huy Trinh [view email] [v1] Tue, 28 Jul 2026 19:00:17 UTC (657 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Rad-JEPA 3D: Radiology Joint-Embedding Predictive Model for 3D Computed Tomography, by Quoc-Huy Trinh and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new | recent | 2026-07
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)