mlsanityData to 14 Oct 2026

CURE: Curriculum-guided Multi-task Training for Reliable Anatomy Grounded Report Generation

arXiv 2601.15408 ↗First posted 21 Jan 2026cs.CV cs.AI cs.CLcited by 1

On the map: Multimodal LLMs / vision-language models → Medical vision-language models

Abstract (arXiv)

Medical vision-language models can automate the generation of radiology reports but struggle with accurate visual grounding and factual consistency. Existing models often misalign textual findings with visual evidence, leading to unreliable or weakly grounded predictions. We present CURE, an error-aware curriculum learning framework that improves grounding and report quality without any additional data. CURE fine-tunes a multimodal instructional model on phrase grounding, grounded report generation, and anatomy-grounded report generation using public datasets. The method dynamically adjusts sampling based on model performance, emphasizing harder samples to improve spatial and textual alignment. CURE improves grounding accuracy by +0.35 IoU, boosts report quality by +0.192 CXRFEScore, and reduces hallucinations by 18.6%. CURE is a data-efficient framework that enhances both grounding accuracy and report reliability. Code is available at https://github.com/PabloMessina/CURE and model weights at https://huggingface.co/pamessina/medgemma-4b-it-cure

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 35 of its 58 references that are in the map. First posted on arXiv 21 Jan 2026.

Builds on

35 of 58 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Vision Language Models in Medicine24 Feb
  2. 2024VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge19 Nov
  3. 2024Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?6 Nov
  4. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day1 Jun

Other references · 31

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2025Qwen2.5-VL Technical Reportcited by 5,587
  4. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  5. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
  6. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  7. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,729
  8. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  9. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  10. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,188
  11. 2017A Survey on Multi-Task Learningcited by 840
  12. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 821
19 more
  1. 2024Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMscited by 735
  2. 2018Albumentations: fast and flexible image augmentationscited by 560
  3. 2025MedGemma Technical Reportcited by 436
  4. 2020CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERTcited by 337
  5. 2019On The Power of Curriculum Learning in Training Deep Networkscited by 286
  6. 2024MAIRA-2: Grounded Radiology Report Generationcited by 145
  7. 2024RaTEScore: A Metric for Radiology Report Generationcited by 65
  8. 2024Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluationcited by 51
  9. 2024PadChest-GR: A Bilingual Chest X-ray Dataset for Grounded Radiology Report Generationcited by 35
  10. 2025LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuningcited by 28
  11. 2023Behind the Magic, MERLIM: Multi-modal Evaluation Benchmark for Large Image-Language Modelscited by 23
  12. 2018Multi-Task Learning for Left Atrial Segmentation on GE-MRIcited by 16
  13. 2024e-Health CSIRO at RRG24: Entropy-Augmented Self-Critical Sequence Training for Radiology Report Generationcited by 10
  14. 2025EAGLE: Enhanced Visual Grounding Minimizes Hallucinations in Instructional Multimodal Modelscited by 8
  15. 2021Multi-Task, Multi-Domain Deep Segmentation with Shared Representations and Contrastive Regularization for Sparse Pediatric Datasetscited by 5
  16. 2024Extracting and Encoding: Leveraging Large Language Models and Medical Knowledge to Enhance Radiological Text Representationcited by 5
  17. 2021Multi-task fusion for improving mammography screening data classificationcited by 4
  18. 2023Cross-Task Attention Network: Improving Multi-Task Learning for Medical Imaging Applicationscited by 4
  19. 2025DeepChest: Dynamic Gradient-Free Task Weighting for Effective Multi-Task Learning in Chest X-ray Classificationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Precision Recall Controllable Radiology Report Generation via Hybrid Natural Language and Clinical Reward Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Visual Alignment of Medical Vision-Language Models for Grounded Radiology Report Generation
  2. 2026Enhancing Fine-Grained Spatial Grounding in 3D CT Report Generation via Discriminative Guidance
  3. 2026MedScribe: Clinically Grounded CT Reporting through Agentic Workflows
  4. 2025RadHiera: Semantic Hierarchical Reinforcement Learning for Medical Report Generation
  5. 2025Reason Like a Radiologist: Chain-of-Thought and Reinforcement Learning for Verifiable Report Generation
  6. 2025Look & Mark: Leveraging Radiologist Eye Fixations and Bounding boxes in Multimodal Large Language Models for Chest X-ray Report Generation
  7. 2026RadPRISM: Schema-stratified radiology-report supervision for concept-disentangled image representations and visual grounding
  8. 2025MRG-R1: Reinforcement Learning for Clinically Aligned Medical Report Generation