← Search

Mingzheng Zhang

2 accepted papers

2026

A Progressive Evidence Localization Framework Based on Wasserstein Gradient Flows for Document Visual Question Answering

ICML 2026poster

Precise evidence region localization in Document Visual Question Answering (DocVQA) is crucial for improving model interpretability and reliability. However, most existing approaches rely on single-step localization, which struggles to effectively distinguish true evidence from irrelevant content wh…

Cited by 0SourceScholar
2026

NeuroRule: Bridging Vision and Logic with Differentiable Rule Induction

CVPR 2026

Scene Graph Generation (SGG) aims to structurally represent visual scenes by detecting objects and their pairwise relationships. Despite significant progress, current models encode visual knowledge with ambiguous visual context and logically inferred implicit relations due to their purely neural, pi

Cited by 0SourceScholar