1
FSA-GRPO: Teaching Auditory LLMs to Use Few-shot Demonstrations
听觉大模型新突破，FSA-GRPO方法教会模型巧用少样本演示，大幅提升推理与适应能力。
arXiv:2606.02615v1 Announce Type: cross Abstract: Few-shot prompting provides an effective way to adapt auditory large language models to low-resource…