Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming
15h ago
Quick Take
A new framework enhances ultrasound diagnosis by integrating interactive zooming and uncertainty-aware rewards.
Key Points
- Introduces Zoom-then-Diagnose paradigm for lesion-focused reasoning.
- Implements uncertainty-aware rewards to boost model confidence.
- Achieves 39.3% improvement in lesion localization across datasets.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →arXiv cs.CV·Jinhao Jing, Zheng Ma, Jinwei Liang, Qiannian Zhao, Shawn Chen, Jing Yang, Por Lip Yee, Prayag Tiwari, Jingjing Bai, Benyou Wang, Lewei Lu, Zhan Su
3d ago FeaturedOriginal
GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning
AI Summary
GeoSym127K introduces a scalable neuro-symbolic framework for enhanced geometric reasoning in multimodal models.