@article{statefulvisualencodersforvisionlanguagem,
  title = {Stateful Visual Encoders for Vision-Language Models},
  author = {Zirui Wang and Junwei Yu and Adam Yala and David M. Chan and Joseph E. Gonzalez and Trevor Darrell},
  year = {2026},
  eprint = {2606.04433},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.04433},
}