@article{thisthatlanguagegesturecontrolledvideo, title = {This&That: Language-Gesture Controlled Video Generation for Robot Planning}, author = {Boyang Wang and Nikhil Sridhar and Chao Feng and Mark Van der Merwe and Adam Fishman and Nima Fazeli and Jeong Joon Park}, year = {2024}, eprint = {2407.05530}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.05530v2}, }