@article{longllavascalingmultimodalllmsto1000,
  title = {LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture},
  author = {Xidong Wang and Dingjie Song and Shunian Chen and Chen Zhang and Benyou Wang},
  year = {2024},
  eprint = {2409.02889},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.02889v2},
}