Update README.md

README.md

@@ -13,7 +13,7 @@ pipeline_tag: audio-text-to-text
 
 R1-AQA is a audio question answering (AQA) model based on `Qwen2-Audio-7B-Instruct`, optimized through reinforcement learning using the group relative policy optimization (GRPO) algorithm. 
 This implementation has achieved state-of-the-art performance on MMAU *Test-mini* benchmark with only 38k post-training samples.
-For more details, please refer to our [Github](https://github.com/xiaomi/r1-aqa) and [Technical Report](https://arxiv.org/abs/2503.11197).
+For more details, please refer to our [Github](https://github.com/xiaomi-research/r1-aqa) and [Technical Report](https://arxiv.org/abs/2503.11197).
 
 ### Table: Accuracies (%) on MMAU Test-mini benchmark
 | Model                                      | Method                  | Sound  | Music  | Speech | Average |