Recursive Vision Transformer with Dynamic Depth and Width Adjustment for Resource-Efficient Image Semantic Communication

Zhilong Zhang, Xinhui Zhang, Gongyu Jin, Sihua Wang, Danpu Liu, Changchuan YinarXiv 2026 · DOI

BibTeX
@misc{zhang2026recursive,
  author = {Zhilong Zhang and Xinhui Zhang and Gongyu Jin and Sihua Wang and Danpu Liu and Changchuan Yin},
  title = {{Recursive Vision Transformer with Dynamic Depth and Width Adjustment for Resource-Efficient Image Semantic Communication}},
  year = {2026},
  eprint = {2606.00114},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.00114},
}

Loading related content...

Figure