mlsanityData to 7 Oct 2026

EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence

arXiv 2509.14977 ↗First posted 18 Sep 2025cs.CVcited by 5

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

also in 1 more
Abstract (arXiv)

Ultrasound is the preferred early cancer screening modality due to non-ionizing radiation, cost-effectiveness, and real-time imaging, yet conventional diagnosis relies heavily on physician expertise, causing significant subjectivity and limited efficiency. Vision-Language Models (VLMs) show promise but lack ultrasound-specific knowledge and multi-organ generalization. We propose EchoVLM, the first open-source 10-billion-parameter ultrasound-tailored VLM with a Mixture-of-Experts (MoE) architecture. It is infused with knowledge across seven anatomical systems, trained on 208,941 clinical cases, 1.47 million ultrasound key-frame images, and over 100 diseases or imaging findings. Supporting clinical report generation, diagnosis prediction, and Visual Question Answering (VQA), it outperforms Qwen2-VL by 7.58 BLEU-1 and 3.45 ROUGE-1 points in report generation. This work shows substantial potential for establishing a general-purpose ultrasound VLM and lays a technical foundation for clinical translation. Source code and model weights are available at https://github.com/Asunatan/EchoVLM.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 18 of its 40 references that are in the map. First posted on arXiv 18 Sep 2025.

Builds on

18 of 40 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning8 Jun
  2. 2024HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale27 Jun
  3. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day1 Jun

Other references · 15

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  4. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  5. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
  6. 2023Video-LLaVA: Learning United Visual Representation by Alignment Before Projectioncited by 1,385
  7. 2023VILA: On Pre-training for Visual Language Modelscited by 686
  8. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuningcited by 439
  9. 2023LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understandingcited by 272
  10. 2024CogVLM2: Visual Language Models for Image and Video Understandingcited by 214
  11. 2024OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understandingcited by 126
  12. 2023MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Trainingcited by 96
3 more
  1. 2024From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Taskscited by 37
  2. 2025FetalCLIP: A Visual-Language Foundation Model for Fetal Ultrasound Image Analysiscited by 21
  3. 2024Ultrasound Report Generation with Cross-Modality Feature Alignment via Unsupervised Guidancecited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026When Minor Edits Matter: LLM-Driven Prompt Attack for Medical VLM Robustness in Ultrasoundcited by 0
  2. 2026Echo-α: Large Agentic Multimodal Reasoning Model for Ultrasound Interpretationcited by 0
  3. 2026Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zoomingcited by 0
  4. 2026EchoSonar-R: A Multi-View Reasoning-Enabled Model for Disease Classification and Report Generation in Echocardiographycited by 0
  5. 2026Towards Real-World Ultrasound Understanding: Large Vision-Language Models from Multi-Image Examinations with Long-Form Reportscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound Understanding
  2. 2025UMind-VL: A Generalist Ultrasound Vision-Language Model for Unified Grounded Perception and Comprehensive Interpretation
  3. 2026Automated Report-Derived Oncology VQA Benchmark for Evaluating Vision-Language Models on 3D Medical Imaging
  4. 2026Boot-and-Feedback Framework for Generalist-Expert Model Collaboration in Breast Ultrasound Diagnosis
  5. 2025Grounding DINO-US-SAM: Text-Prompted Multi-Organ Segmentation in Ultrasound with LoRA-Tuned Vision-Language Models
  6. 2025EchoVLM: Measurement-Grounded Multimodal Learning for Echocardiography
  7. 2026UltraG-Bench: A Multi-task Benchmark for assessing Large Vision-Language Models on Pixel-level Evidence Grounding in Ultrasound
  8. 2025FETAL-GAUGE: A Benchmark for Assessing Vision-Language Models in Fetal Ultrasound