Update README.md

README.md

@@ -24,6 +24,6 @@ pipeline_tag: video-text-to-text
 
 ROMA introduces a "Speak Head" mechanism to decouple response timing from content generation, allowing it to autonomously decide *when* to speak based on the continuous audio-visual stream.
 
-- **Paper:** [ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding](https://arxiv.org/abs/250x.xxxxx)
+- **Paper:** [ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding](https://arxiv.org/abs/2601.10323)
 - **Project Page:** [Link](https://eureka-maggie.github.io/ROMA_show/)
 - **Repository:** [[Github (Coming Soon)](https://github.com/Eureka-Maggie/ROMA)]