@misc{arxiv_2609_15215,
  title = {Augmenting Large Audio-Language Models with Frame-Level Grounding for Fine-Grained Temporal Perception},
  author = {{Yanfeng Shi} and {Yan Song} and {Junhui Li} and {Tinggan Huang} and {Wu Guo} and {Haoyu Song} and {Ian McLoughlin}},
  eprint = {2609.15215},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.15215}
}