CoViST: Visual Token Compression via Composable States
Visual token compression lowers the inference cost of vision--language models by representing images with fewer tokens. However, most existing methods compress visual tokens to a reduced set, leaving the amount of visual evidence represented by each token and its original spatial context implicit. Therefore, the compre...
Qi Zhang, Xian-Dong Meng, Rong-Gang Wang et al.
· 0 citations