Update README.md

README.md

@@ -39,7 +39,7 @@ Please note: For individuals  or organizations generating annual revenue of US $
 * **Model details**: This model is trained to generate 48 images (12 video frames x 4 camera views) at 576x576 resolution, given a reference video of 12 frames of the same size. 
 The generated 12x4 images matrix can be viewed as 4 videos (12 frames each), showing how the dynamic object looks from 4 different camera angles specified by the user.
 To generate longer novel-view videos, we use the first generated frames as reference, and then sample the remaining frames in an auto-regressive manner.
-Please check our [tech report](https://sv4d2.0.github.io/static/sv4d2.0_tech_report.pdf) and [video summary](https://youtu.be/dtqj-s50ynU?feature=shared) for details.
+Please check our [arxiv paper](https://arxiv.org/pdf/2503.16396) and [video summary](https://youtu.be/dtqj-s50ynU?feature=shared) for details.
 
 
 ### License
@@ -50,10 +50,9 @@ Please check our [tech report](https://sv4d2.0.github.io/static/sv4d2.0_tech_rep
 ### Model Sources
 
 * **Repository**: https://github.com/Stability-AI/generative-models
-* **Tech report**: https://sv4d2.0.github.io/static/sv4d2.0_tech_report.pdf
-* **Video summary**: https://youtu.be/dtqj-s50ynU?feature=shared
 * **Project page**: https://sv4d20.github.io
-* **arXiv page**: https://arxiv.org/pdf/2503.16396
+* **arXiv paper**: https://arxiv.org/pdf/2503.16396
+* **Video summary**: https://youtu.be/dtqj-s50ynU?feature=shared
 
 
 ### Training Dataset