arXiv Machine Learning August 12, 2026 By Amoon Jamzad, Dilakshan Srikanthan, Faranak Akbarifar, Nooshin Maghsoodi, Parvin Mousavi

P3CA: Encoder-Agnostic Interpretation of Vision Foundation Model Embeddings via Spatial Probing

Read the original on arXiv Machine Learning →

arXiv:2608. 10131v1 Announce Type: cross Abstract: Vision foundation models are increasingly used as reusable encoders in medical image computing, yet their high-dimensional spatial embeddings are difficult to inspect beyond downstream task performance or global dimensionality reduction.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Aug 7

Big, Bright, or Invisible: A Frozen-Feature Benchmark of 3D CT Foundation Models

arXiv:2608. 05960v1 Announce Type: cross Abstract: Routine CT interpretation is inherently comprehensive, capturing incidental findings across the entire scan volume.

By Maulik Chevli, Johannes Brandt, Rickmer Braren, Daniel Rueckert, Philip M\"uller

llms rag nlp multimodal benchmarks safety

arXiv AI

5d ago

Mr3D-VL: A generalist vision language foundation model for Multiparametric 3D Magnetic Resonance Imaging

arXiv:2608. 12689v1 Announce Type: cross Abstract: Multi-parametric magnetic resonance imaging (mpMRI) is a cornerstone for brain tumor diagnosis and treatment, yet current AI models face critical limitations: their lack of natural language interaction and interpretability impedes spatial information integration and cross-modal reasoning required clinically.

By Zhi Qiao, Xintong Wu, Yichu He, Feng Shi

llms rag multimodal safety

arXiv AI

1d ago

PaSTel: Anchoring Histology in Spatial Transcriptomics via Multi-Scale Hierarchical Bio-Prior Contrastive Pretraining

arXiv:2608. 14924v1 Announce Type: cross Abstract: Spatial transcriptomics (ST) links tissue morphology with molecular programs, motivating multimodal pretraining methods that align histology images with gene expression.

By Azim Dehghani Amirabad, Junchao Zhu, Pushpak Pati, Walid Abdelmoula, Tommaso Mansi, Rui Liao

multimodal safety

Hugging Face Trending Papers

Jul 29

MedARC: Training-Free Adaptive Redundancy Compression of Visual Tokens for 3D Medical Vision-Language Models

Integrating 3D medical images with vision-language models (VLMs) holds substantial promise for computer-aided diagnosis. However, volumetric images generate prohibitively long visual-token sequences with considerable spatial and inter-slice redundancy.

llms rag multimodal

arXiv AI

Jun 30

One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models

arXiv:2606. 29600v1 Announce Type: cross Abstract: A faithful 3D world representation should account for layered geometry, where a single camera ray may contain multiple visible and geometrically valid surfaces.

By Xiaohao Xu, Feng Xue, Xiang Li, Haowei Li, Shusheng Yang, Tianyi Zhang, Matthew Johnson-Roberson, Xiaonan Huang

llms computer-vision benchmarks

arXiv AI

Jul 24

Sparse Concept Channels in Frozen 3D CT Vision Encoders

arXiv:2607. 20993v1 Announce Type: cross Abstract: Large vision-language models are becoming increasingly dominant in 3D medical image interpretation, but we rarely know which internal units encode clinical findings or where that information lives in the representation.

By Farhad Nooralahzadeh, Lea Bogensperger, Christian Bluethgen, Michael Krauthammer

llms rag multimodal

Related stories

Big, Bright, or Invisible: A Frozen-Feature Benchmark of 3D CT Foundation Models

Mr3D-VL: A generalist vision language foundation model for Multiparametric 3D Magnetic Resonance Imaging

PaSTel: Anchoring Histology in Spatial Transcriptomics via Multi-Scale Hierarchical Bio-Prior Contrastive Pretraining

MedARC: Training-Free Adaptive Redundancy Compression of Visual Tokens for 3D Medical Vision-Language Models

One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models

Sparse Concept Channels in Frozen 3D CT Vision Encoders