CORD: Bridging the Audio-Text Reasoning Gap via Weighted On-policy Cross-modal Distillation

Jing Hu, Danxiang Zhu, Xianlong Luo, Dan Zhang, Shuwei He, Yishu Lei, Haitao Zheng, Shikun Feng, Jingzhou He, Yu Sun, Hua Wu, Haifeng WangarXiv 2026 · DOI

BibTeX
@misc{hu2026cord,
  author = {Jing Hu and Danxiang Zhu and Xianlong Luo and Dan Zhang and Shuwei He and Yishu Lei and Haitao Zheng and Shikun Feng and Jingzhou He and Yu Sun and Hua Wu and Haifeng Wang},
  title = {{CORD: Bridging the Audio-Text Reasoning Gap via Weighted On-policy Cross-modal Distillation}},
  year = {2026},
  eprint = {2601.16547},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.16547},
}

Loading related content...

Figure