@article{gondolagroundedvisionlanguageplanningfor, title = {Gondola: Grounded Vision Language Planning for Generalizable Robotic Manipulation}, author = {ShiZhe Chen and Ricardo Garcia and Paul Pacaud and Cordelia Schmid}, year = {2025}, eprint = {2506.11261}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.11261v1}, }