@article{towardsthevisionsoundlanguageactionparad, title = {Towards the Vision-Sound-Language-Action Paradigm: The HEAR Framework for Sound-Centric Manipulation}, author = {Chang Nie and Tianchen Deng and Guangming Wang and Zhe Liu and Hesheng Wang}, year = {2026}, eprint = {2603.16086}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.16086}, }