neurips note 4m-21

app.py

@@ -107,7 +107,7 @@ with gr.Blocks(css=css, theme=gr.themes.Base()) as demo:
                 gr.Markdown(f"""
                 *A framework for training any-to-any multimodal foundation models. Scalable. Open-sourced. Across tens of modalities and tasks.*
                 
-                [`Website`](https://4m.epfl.ch) | [`GitHub`](https://github.com/apple/ml-4m) <br>[`4M Paper (NeurIPS'23)`](https://arxiv.org/abs/2312.06647) | [`4M-21 Paper (arXiv'24)`](https://arxiv.org/abs/2406.09406)
+                [`Website`](https://4m.epfl.ch) | [`GitHub`](https://github.com/apple/ml-4m) <br>[`4M Paper (NeurIPS'23)`](https://arxiv.org/abs/2312.06647) | [`4M-21 Paper (NeurIPS'24)`](https://arxiv.org/abs/2406.09406)
 
                 This demo predicts all modalities from a given RGB input, using [{FM_MODEL_ID}](https://huggingface.co/{FM_MODEL_ID}), running on *{power_device}*.
                 For more generative any-to-any examples, please see our [GitHub repo](https://github.com/apple/ml-4m#generation).