arXiv AI September 17, 2026 By Daniele Molino, Camillo Maria Caruso, Filippo Ruffini, Paolo Soda, Valerio Guarrasi

From Alignment to Synthesis: Contrastive Volumetric Grounding for Text-to-CT Generation

The paper introduces a 3D-CLIP encoder trained with structured hard negatives to improve vision‑language alignment for text‑to‑CT generation. This encoder drives a latent diffusion model that operates directly in 3D latent space, eliminating spatial artifacts from super‑resolution pipelines. Experiments on the CT‑RATE dataset show state‑of‑the‑art image fidelity and factual correctness across 18 pathological conditions, with lower inference time and GPU memory usage than competing methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Aug 11

From Alignment to Synthesis Contrastive Volumetric Grounding for Text-to-CT Generation

arXiv:2506. 00633v3 Announce Type: replace-cross Abstract: Generating semantically controllable 3D CT volumes from radiology reports requires more than a rich text encoder, it requires vision-language alignment grounded in volumetric space.

By Daniele Molino, Camillo Maria Caruso, Filippo Ruffini, Paolo Soda, Valerio Guarrasi

diffusion multimodal benchmarks safety

arXiv AI

Aug 11

Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation

arXiv:2608. 08713v1 Announce Type: cross Abstract: Vision-language models offer a promising path toward automating radiology report generation, but applying them to full 3D CT volumes poses substantial computational challenges.

By Jonathan Suprijadi, Raphael Stock, Moritz Langenberg, David Zimmerer, Kim-Celine Kahl, Stefan Denner, Yannick Kirchhoff, Karol Gotkowski, Maximilian Rokuss, Jeremias Traub, Tassilo Wald, Constantin Ulrich, Klaus Maier-Hein

llms multimodal benchmarks

arXiv Machine Learning

Aug 18

Comprehensive language-image pre-training for 3D medical image understanding

arXiv:2510. 15042v3 Announce Type: replace-cross Abstract: In the 3D medical image domain, vision-language pre-training is used to create vision-language encoders (VLEs) that can support radiologists by retrieving patients with similar abnormalities, predicting likelihoods of abnormality, or, with downstream adaptation, generating radiological reports.

By Tassilo Wald, Ibrahim Ethem Hamamci, Yuan Gao, Sam Bond-Taylor, Harshita Sharma, Maximilian Ilse, Cynthia Lo, Olesya Melnichenko, Anton Schwaighofer, Noel C. F. Codella, Maria Teodora Wetscherek, Klaus H. Maier-Hein, Panagiotis Korfiatis, Valentina Salvatelli, Javier Alvarez-Valle, Fernando P\'erez-Garc\'ia

computer-vision multimodal benchmarks safety

arXiv Computer Vision

Sep 10

Anatomy-Grounded Weakly Supervised Prompt Tuning for Chest X-ray Latent Diffusion Models

arXiv:2506.10633v2 Announce Type: replace Abstract: Latent Diffusion Models have shown remarkable results in text-guided image synthesis in recent years. In the domain of natural (RGB) images, recent...

By Konstantinos Vilouras, Ilias Stogiannidis, Junyu Yan, Alison Q. O'Neil, Sotirios A. Tsaftaris

diffusion fine-tuning multimodal benchmarks safety

arXiv Computer Vision

Oct 8

PhyDiCT: Plug-and-Play CT Reconstruction from Sparse X-Rays via Differentiable Rendering and Strong Priors

arXiv:2610.09253v1 Announce Type: new Abstract: Reconstructing 3D Computed Tomography (CT) images from a few X-ray projections is a highly ill-posed inverse problem due to the loss of volumetric info...

By Weicheng Dai, Shantanu Ghosh, Kayhan Batmanghelich

diffusion fine-tuning

arXiv Machine Learning

Oct 8

ORCA: Hunting Compositional Failures in Text-to-Image Diffusion

ORCA (Orthogonal Residual Compositional Alignment) is a method that improves text-to-image diffusion models by aligning the diffusion transformer’s latent space with a low‑rank target derived from a frozen visual encoder. It introduces an auxiliary loss that uses a predictor with an orthogonal basis parameterised by a learned residual between T5 and CLIP embeddings, providing a prompt‑dependent signal for selecting the visual readout subspace. Experiments on three diffusion‑transformer backbones show that ORCA improves FID and GenEval scores, especially on attribute binding, spatial relations, and multi‑object prompts, without adding inference‑time cost.

By Arshia Hemmat, Amirhossein Vahidi, Amitis Shidani, Mohammad Vali Sanian, Hesam Asadollahzadeh, Aryan Yazdan Parast, Mohammad Lotfollahi

llms rag diffusion multimodal safety