@article{geminifusionefficientpixelwisemultimodal,
  title = {GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer},
  author = {Ding Jia and Jianyuan Guo and Kai Han and Han Wu and Chao Zhang and Chang Xu and Xinghao Chen},
  year = {2024},
  eprint = {2406.01210},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.01210v2},
}