CRISPR: Context-Refined Information Spatial Pooling with Region-awareness for Efficient Visual Token Compression in VLMs
This paper proposes CRISPR, a context-refined information spatial pooling framework with region-awareness for visual token compression, and demonstrates that CRISPR consistently outperforms low-resolution baselines at a comparable compressed sequence length.
Zuyi Zhou, Di-Zhan Xue, Sheng-Sheng Qian et al.
· 0 citations