@article{comevlscalingcomplementarymultiencodervi,
  title = {CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning},
  author = {Ankan Deria and Komal Kumar and Xilin He and Imran Razzak and Hisham Cholakkal and Fahad Shahbaz Khan and Salman Khan},
  year = {2026},
  eprint = {2604.03231},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.03231},
}