update

README.md

@@ -12,8 +12,8 @@ tags:
   - zero-shot
   - audio-text
 ---
-# Mellow
-[[`Paper`]()] [[`GitHub`](https://github.com/soham97/Mellow)] [[`Checkpoint`](https://huggingface.co/soham97/Mellow)] [[`Zenodo`](https://zenodo.org/records/15002886)]
+# Mellow: a small audio language model for reasoning
+[[`Paper`](https://arxiv.org/abs/2503.08540)] [[`GitHub`](https://github.com/soham97/Mellow)] [[`Checkpoint`](https://huggingface.co/soham97/Mellow)] [[`Zenodo`](https://zenodo.org/records/15002886)]
 
 Mellow is a small Audio-Language Model that takes in two audios and a text prompt as input and produces free-form text as output. It is a 167M parameter model and trained on ~155 hours of audio (AudioCaps and Clotho), and achieves SoTA performance on different tasks with 50x fewer parameters. 
 
@@ -96,5 +96,13 @@ With Mellow, we aim to showcase that small audio-language models can engage in r
 
 ## Citation
 ```
-
+@misc{mellow,
+      title={Mellow: a small audio language model for reasoning}, 
+      author={Soham Deshmukh and Satvik Dixit and Rita Singh and Bhiksha Raj},
+      year={2025},
+      eprint={2503.08540},
+      archivePrefix={arXiv},
+      primaryClass={cs.SD},
+      url={https://arxiv.org/abs/2503.08540}, 
+}
 ```