@article{scenealignaligningmultimodalreasoningtos,
  title = {SceneAlign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual Scenes},
  author = {Chuhan Wang and Xintong Li and Jennifer Yuntong Zhang and Junda Wu and Chengkai Huang and Lina Yao and Julian McAuley and Jingbo Shang},
  year = {2026},
  eprint = {2601.05600},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.05600},
}