@article{inserterspeechinstructionfollowingwith, title = {InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training}, author = {Dingdong Wang and Jin Xu and Ruihang Chu and Zhifang Guo and Xiong Wang and Jincenzi Wu and Dongchao Yang and Shengpeng Ji and Junyang Lin}, year = {2025}, eprint = {2503.02769}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.02769v2}, }