@article{stvlmkinematicinstructiontuningfor,
  title = {ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language Models},
  author = {Dohwan Ko and Sihyeon Kim and Yumin Suh and Vijay Kumar B. G and Minseo Yoon and Manmohan Chandraker and Hyunwoo J. Kim},
  year = {2025},
  eprint = {2503.19355},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.19355v2},
}