Revealing the Impact of Visual Text Style on Attribute-based Descriptions Produced by Large Visual Language Models

arXiv:2604.27553 · cs.CV, cs.CL · Submitted 2026-04-30 · Read on arXiv

cs.CV, cs.CL

Submitted: 2026-04-30

Updated: 2026-04-30

Comments: Accepted by ICMR 2026. Code is available at https://github.com/XiaomengWang-AI/The-Impact-of-Visual-Text-style-on-Attribute-based-Descriptions-Produced-by-LVLMs

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Large Visual Language Model — 2× in this paper

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models