@article{ageneraloneshotmultimodalactiveperceptio,
  title = {A General One-Shot Multimodal Active Perception Framework for Robotic Manipulation: Learning to Predict Optimal Viewpoint},
  author = {Deyun Qin and Zezhi Liu and Hanqian Luo and Xiao Liang and Yongchun Fang},
  year = {2026},
  eprint = {2601.13639},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.13639},
}