@article{attentionawareinferenceoptimizationsforl,
  title = {Attention-aware Inference Optimizations for Large Vision-Language Models with Memory-efficient Decoding},
  author = {Fatih Ilhan and Gaowen Liu and Ramana Rao Kompella and Selim Furkan Tekin and Tiansheng Huang and Zachary Yahn and Yichang Xu and Ling Liu},
  year = {2026},
  eprint = {2603.23914},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.23914},
}