@misc{arxiv_2610_21588v1,
  title = {Hear, Localize, and Reason: Spatially Aware Scene Understanding for Audio-Visual LLMs},
  author = {{Kim Sung-Bin} and {Lee Jung-Mok} and {Jinwoo Jung} and {Oh Hyun-Bin} and {Hyeonggon Ryu} and {David Harwath} and {Tae-Hyun Oh}},
  eprint = {2610.21588v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.21588v1}
}