@article{learningtopredictmiddlelayerattentioninm, title = {Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Pruning}, author = {Yuyao Sun and Tao Deng and Shuang Li and Deqing Wang and Hao Geng and Minjun Yu}, year = {2026}, eprint = {2608.06411}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.06411}, }