@article{groundingmultimodallargelanguagemodelsin, title = {Grounding Multimodal Large Language Models in Actions}, author = {Andrew Szot and Bogdan Mazoure and Harsh Agrawal and Devon Hjelm and Zsolt Kira and Alexander Toshev}, year = {2024}, eprint = {2406.07904}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.07904v2}, }