@article{avamuniversaltrainingfreeadaptivevisuala,
  title = {AVAM: Universal Training-free Adaptive Visual Anchoring Embedded into Multimodal Large Language Model for Multi-image Question Answering},
  author = {Kang Zeng and Guojin Zhong and Jintao Cheng and Jin Yuan and Zhiyong Li},
  year = {2025},
  eprint = {2508.17860},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.17860},
}