@article{visionasinversegraphicsagentviainterleav,
  title = {Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning},
  author = {Shaofeng Yin and Jiaxin Ge and Zora Zhiruo Wang and Chenyang Wang and Xiuyu Li and Michael J. Black and Trevor Darrell and Angjoo Kanazawa and Haiwen Feng},
  year = {2026},
  eprint = {2601.11109},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.11109},
}