EvidenceConnect增强视觉证据连接
AI 总结
Lai Wei等13位作者于2026年10月27日向arXiv提交《Zooming without Zooming v2》,提出EvidenceConnect合成数据框架,利用单张图像中相关区域的放大视图生成训练问题。研究者使用RLVR训练基础视觉语言模型,得到Zooming without Zooming v2(ZwZ2)。作者报告称,该方法在细粒度与空间感知、具身空间推理、多模态长上下文理解、多模态智能体任务及通用视觉推理方面均有提升。
深度见解
该论文提供了一种生成视觉证据连接训练数据的具体方法,并报告其在空间感知、长上下文推理和智能体任务上的改进。
Computer Science > Computer Vision and Pattern Recognition
arXiv:2610.37037 (cs)
[Submitted on 27 Oct 2026]
Title:Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception
Authors:Lai Wei, Yatai Li, Liangbo He, Jun Lan, Renjie Gu, Linhan Cao, Junkai Lin, Huijia Zhu, Weiqiang Wang, Linghe Kong, Yue Wang, Zhuosheng Zhang, Weiran Huang
View a PDF of the paper titled Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception, by Lai Wei and 12 other authors