Auto-Controlled Image Perception in MLLMs via Visual Perception Tokens

Runpeng Yu, Xinyin Ma, Xinchao Wang. Auto-Controlled Image Perception in MLLMs via Visual Perception Tokens. In IEEE/CVF International Conference on Computer Vision, ICCV 2025, Honolulu, HI, USA, October 19-25, 2025. pages 21822-21831, IEEE, 2025. [doi]

Authors

Runpeng Yu

This author has not been identified. Look up 'Runpeng Yu' in Google

Xinyin Ma

This author has not been identified. Look up 'Xinyin Ma' in Google

Xinchao Wang

This author has not been identified. Look up 'Xinchao Wang' in Google