Link model to paper and add metadata

README.md

@@ -1,13 +1,16 @@
 ---
 license: mit
 pipeline_tag: any-to-any
+library_name: transformers
 tags:
 - Audio-to-Text
 - Text-to-Audio
 - Audio-to-Audio
 - Text-to-Text
 - Audio-Text-to-Text
+arxiv: 2512.23808
 ---
+
 <div align="center">
   <picture>
     <source srcset="https://github.com/XiaomiMiMo/MiMo-VL/raw/main/figures/Xiaomi_MiMo_darkmode.png?raw=true" media="(prefers-color-scheme: dark)">
@@ -32,7 +35,7 @@ tags:
   |
   <a href="https://github.com/XiaomiMiMo/MiMo-Audio" target="_blank">🤖 GitHub</a>
   &nbsp;|
-  <a href="https://github.com/XiaomiMiMo/MiMo-Audio/blob/main/MiMo-Audio-Technical-Report.pdf" target="_blank">📄 Paper</a>
+  <a href="https://huggingface.co/papers/2512.23808" target="_blank">📄 Paper</a>
   &nbsp;|
   <a href="https://xiaomimimo.github.io/MiMo-Audio-Demo" target="_blank">📰 Blog</a>
   &nbsp;|
@@ -50,6 +53,8 @@ tags:
 
 Existing audio language models typically rely on task-specific fine-tuning to accomplish particular audio tasks. In contrast, humans are able to generalize to new audio tasks with only a few examples or simple instructions. GPT-3 has shown that scaling next-token prediction pretraining enables strong generalization capabilities in text, and we believe this paradigm is equally applicable to the audio domain. By scaling MiMo-Audio's pretraining data to over one hundred million of hours, we observe the emergence of few-shot learning capabilities across a diverse set of audio tasks. We develop a systematic evaluation of these capabilities and find that MiMo-Audio-7B-Base achieves SOTA performance on both speech intelligence and audio understanding benchmarks among open-source models. Beyond standard metrics, MiMo-Audio-7B-Base generalizes to tasks absent from its training data, such as voice conversion, style transfer, and speech editing. MiMo-Audio-7B-Base also demonstrates powerful speech continuation capabilities, capable of generating highly realistic talk shows, recitations, livestreaming and debates. At the post-training stage, we curate a diverse instruction-tuning corpus and introduce thinking mechanisms into both audio understanding and generation. MiMo-Audio-7B-Instruct achieves open-source SOTA on audio understanding benchmarks, spoken dialogue benchmarks and instruct-TTS evaluations, approaching or surpassing closed-source models.
 
+This repository contains the model weights for **MiMo-Audio**, presented in the paper [MiMo-Audio: Audio Language Models are Few-Shot Learners](https://huggingface.co/papers/2512.23808).
+
 <p align="center">
   <img width="95%" src="https://github.com/XiaomiMiMo/MiMo-Audio/blob/main/assets/Results.png?raw=true">
 </p>
@@ -73,7 +78,7 @@ MiMo-Audio couples a patch encoder, an LLM, and a patch decoder to improve model
 ##  Explore MiMo-Audio Now! 🚀🚀🚀
 - 🎧 **Try the Hugging Face demo:** [MiMo-Audio Demo](https://huggingface.co/spaces/XiaomiMiMo/mimo_audio_chat)
 - 📰 **Read the Official Blog:** [MiMo-Audio Blog](https://xiaomimimo.github.io/MiMo-Audio-Demo)
-- 📄 **Dive into the Technical Report:** [MiMo-Audio Technical Report](https://github.com/XiaomiMiMo/MiMo-Audio/blob/main/MiMo-Audio-Technical-Report.pdf)
+- 📄 **Dive into the Technical Report:** [MiMo-Audio Technical Report](https://huggingface.co/papers/2512.23808)
 
 
 ## Model Download
@@ -158,7 +163,7 @@ This toolkit is designed to evaluate MiMo-Audio and other recent audio LLMs as m
       title={MiMo-Audio: Audio Language Models are Few-Shot Learners}, 
       author={LLM-Core-Team Xiaomi},
       year={2025},
-      url={GitHub - XiaomiMiMo/MiMo-Audio}, 
+      url={https://huggingface.co/papers/2512.23808}, 
 }
 ```