@article{learningsparsevisualrepresentationsviasp,
  title = {Learning Sparse Visual Representations via Spatial-Semantic Factorization},
  author = {Theodore Zhengde Zhao and Sid Kiblawi and Jianwei Yang and Naoto Usuyama and Reuben Tan and Noel C Codella and Tristan Naumann and Hoifung Poon and Mu Wei},
  year = {2026},
  eprint = {2602.01905},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.01905},
}