Paper Detail
Dongjie Fu, Di Cao, Xize Cheng, Zihan Zhang, Wenxu Jia, Yifu Chen, Shengpeng Ji, Yu Zhang, Tao Jin
While large audio-language models have achieved remarkable progress in auditory perception, they still lag behind text-based large language models in deep logical reasoning, primarily due to the scarcity of high-quality audio reasoning data. To bridge this gap, we propose X$^3$-OPD, a cross-modal on-policy distillation framework that transfers reasoning capabilities from a powerful text teacher to an audio-language student. During training, the student generates reasoning trajectories conditioned on its own acoustic perception, while the teacher provides token-level guidance using matched textual inputs and verified answers. We further construct a three-tier symmetric corpus covering textual reasoning rendered into speech, audio-event reasoning grounded in complex acoustic scenes, and spoken-dialogue reasoning involving paralinguistic cues. This design extends cross-modal distillation beyond textually recoverable content to reasoning grounded in non-linguistic events, prosody, and conversational context. Experiments on MMSU, MMAU, BIG Bench Audio, and MMAR demonstrate that X$^3$-OPD substantially improves audio-grounded reasoning and chain-of-thought quality while largely preserving the model's existing capabilities under domain shift.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{fu2026x,
title = {X\$\textasciicircum{}3\$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment},
author = {Dongjie Fu and Di Cao and Xize Cheng and Zihan Zhang and Wenxu Jia and Yifu Chen and Shengpeng Ji and Yu Zhang and Tao Jin},
year = {2026},
abstract = {While large audio-language models have achieved remarkable progress in auditory perception, they still lag behind text-based large language models in deep logical reasoning, primarily due to the scarcity of high-quality audio reasoning data. To bridge this gap, we propose X\$\textasciicircum{}3\$-OPD, a cross-modal on-policy distillation framework that transfers reasoning capabilities from a powerful text teacher to an audio-language student. During training, the student generates reasoning trajectories conditione},
url = {https://arxiv.org/abs/2607.21550},
keywords = {cs.LG},
eprint = {2607.21550},
archiveprefix = {arXiv},
}
{}