Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes
Evidence-grounded visual reasoning (EGVOR) is proposed, departing from implicit inference, EGVOR reformulates reasoning as the explicit generation of Evidence Atoms–structured triplets that enforce strict spatial-semantic alignment.
Zhao-Yang Wei, Bo-Wen Jiang, Xumeng Han et al.
· International Journal of Com... · 6 citations
· ⚡1