@article{thesoundofsimulationlearningmultimodalsi, title = {The Sound of Simulation: Learning Multimodal Sim-to-Real Robot Policies with Generative Audio}, author = {Renhao Wang and Haoran Geng and Tingle Li and Feishi Wang and Gopala Anumanchipalli and Trevor Darrell and Boyi Li and Pieter Abbeel and Jitendra Malik and Alexei A. Efros}, year = {2025}, eprint = {2507.02864}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.02864}, }