@misc{arxiv_2610_35125v1,
  title = {When Fusion Order Matters: Insights on Progressive Multimodal Representation Learning for Cross-modal Retrieval},
  author = {{Haoxiang Zhao} and {Bin Wang} and {Yaofei Wang} and {Xiao Lan} and {Yunfeng Diao} and {Xu Wang}},
  eprint = {2610.35125v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.35125v1}
}