@article{seeingthroughwordsspeakingthroughpixelsd,
  title = {Seeing Through Words, Speaking Through Pixels: Deep Representational Alignment Between Vision and Language Models},
  author = {Zoe Wanying He and Sean Trott and Meenakshi Khosla},
  year = {2025},
  eprint = {2509.20751},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.20751},
}