Xinkuan Qiu — accepted AI-conference papers

2026

Revisiting Visual Corruptions in LVLMs: A Shape-Texture Perspective on Model Failures

Xinkuan Qiu, Meina Kan, Zhenliang He, Yongbin Zhou, Shiguang Shan

CVPR 2026

Large vision-language models (LVLMs) are highly vulnerable to visual corruptions, substantially compromising their reliability and limiting real-world deployment. Prior work has attributed this degradation primarily to insufficient visual grounding and overreliance on language priors. However, these

Cited by 0 Source ↗Scholar ↗

2025

Benchmarking Multimodal Large Language Models Against Image Corruptions

Xinkuan Qiu, Meina Kan, Yongbin Zhou, Shiguang Shan

ICCV 2025poster

Multimodal Large Language Models (MLLMs) have made significant strides in visual and language tasks. However, despite their impressive performance on standard datasets, these models encounter considerable robustness challenges when processing corrupted images, raising concerns about their reliabilit…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗