3 papers
cs.CV2026
When Token Pruning is Worse than Random: Understanding Visual Token Information in VLLMs
Yahong Wang, Juncheng Wu, Zhangkai Ni +8
Vision Large Language Models (VLLMs) incur high computational costs due to their reliance on hundreds of visual tokens to represent images. While token pruning offers a promising s…
cs.CV2025
Self-Supervised Anatomical Consistency Learning for Vision-Grounded Medical Report Generation
Longzhen Yang, Zhangkai Ni, Ying Wen +3
Vision-grounded medical report generation aims to produce clinically accurate descriptions of medical images, anchored in explicit visual evidence to improve interpretability and f…
eess.IV2025
AFUNet: Cross-Iterative Alignment-Fusion Synergy for HDR Reconstruction via Deep Unfolding Paradigm
Xinyue Li, Zhangkai Ni, Wenhan Yang
Existing learning-based methods effectively reconstruct HDR images from multi-exposure LDR inputs with extended dynamic range and improved detail, but they rely more on empirical d…