mlsanityData to 7 Oct 2026

ReXSonoVQA: A Video QA Benchmark for Procedure-Centric Ultrasound Understanding

arXiv 2604.10916 ↗First posted 13 Apr 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Ultrasound acquisition requires skilled probe manipulation and real-time adjustments. Vision-language models (VLMs) could enable autonomous ultrasound systems, but existing benchmarks evaluate only static images, not dynamic procedural understanding. We introduce ReXSonoVQA, a video QA benchmark with 514 video clips and 514 questions (249 MCQ, 265 free-response) targeting three competencies: Action-Goal Reasoning, Artifact Resolution & Optimization, and Procedure Context & Planning. Zero-shot evaluation of Gemini 3 Pro, Qwen3.5-397B, LLaVA-Video-72B, and Seed 2.0 Pro shows VLMs can extract some procedural information, but troubleshooting questions remain challenging with minimal gains over text-only baselines, exposing limitations in causal reasoning. ReXSonoVQA enables developing perception systems for ultrasound training, guidance, and robotic automation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 33 references that are in the map. First posted on arXiv 13 Apr 2026.

Builds on

16 of 33 references.

References · 16

  1. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,287
  2. 2019HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clipscited by 946
  3. 2022MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answeringcited by 525
  4. 2023Med-Flamingo: a Multimodal Medical Few-shot Learnercited by 387
  5. 2023WhisperX: Time-Accurate Speech Transcription of Long-Form Audiocited by 320
  6. 2023BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Taskscited by 201
  7. 2024OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLMcited by 182
  8. 2024GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AIcited by 96
  9. 2024VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledgecited by 50
  10. 2023Robotic Ultrasound Imaging: State-of-the-Art and Future Perspectivescited by 29
  11. 2024ReXrank: A Public Leaderboard for AI-Powered Radiology Report Generationcited by 24
  12. 2025FetalCLIP: A Visual-Language Foundation Model for Fetal Ultrasound Image Analysiscited by 21
4 more
  1. 2025ReXVQA: A Large-scale Visual Question Answering Benchmark for Generalist Chest X-ray Understandingcited by 20
  2. 2025Towards Embodied Agentic AI: Review and Classification of LLM- and VLM-Driven Robot Autonomy and Interactioncited by 18
  3. 2025U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound Understandingcited by 8
  4. 2025USPilot: An Embodied Robotic Assistant Ultrasound System with Large Language Model Enhanced Graph Plannercited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence
  2. 2026Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming
  3. 2026US-VLA: An Ultrasound Vision-Language-Action Model for Embodied Abdomina
  4. 2025FETAL-GAUGE: A Benchmark for Assessing Vision-Language Models in Fetal Ultrasound
  5. 2026Towards Real-World Ultrasound Understanding: Large Vision-Language Models from Multi-Image Examinations with Long-Form Reports
  6. 2025UMind-VL: A Generalist Ultrasound Vision-Language Model for Unified Grounded Perception and Comprehensive Interpretation
  7. 2026ForceU-VLA: A Force-Aware Vision-Language-Action Model for Embodied Ultrasound Scanning
  8. 2026Ultrasound Operator Guidance Using World Modeling and Retrieval Based Action Planning