Update README.md

README.md

@@ -23,7 +23,7 @@ base_model: facebook/dinov2-base
 
 **[NVIDIA](https://www.nvidia.com/)**     **[University of Modena and Reggio Emilia](https://www.unimore.it/)**     **[ETH Zurich](https://ethz.ch/)**
 
-Alessandro Burzio, Tobias Fischer, Sven Elflein, Qunjie Zhou, Riccardo de Lutio, Jiawei Ren, Jiahui Huang, Shengyu Huang, Marc Pollefeys, Laura Leal-Taixé, Zan Gojcic, Haithem Turki
+[Alessandro Burzio](https://research.nvidia.com/labs/dvl/author/alessandro-burzio/), [Tobias Fischer](https://tobiasfshr.github.io/), [Sven Elflein](https://selflein.github.io/), [Qunjie Zhou](https://research.nvidia.com/labs/dvl/author/qunjie-zhou/), [Riccardo de Lutio](https://riccardodelutio.github.io/), [Jiawei Ren](https://jiawei-ren.github.io/), [Jiahui Huang](https://huangjh-pub.github.io/), [Shengyu Huang](https://shengyuh.github.io/), [Marc Pollefeys](https://people.inf.ethz.ch/marc.pollefeys/), [Laura Leal-Taixé](https://research.nvidia.com/labs/dvl/author/laura-leal-taixe/), [Zan Gojcic](https://zgojcic.github.io/), [Haithem Turki](https://haithemturki.com/)
 </div>
 
 # Model Overview
@@ -691,7 +691,7 @@ DVLT is trained on a mixture of 28 public datasets. Per-dataset realized mix sha
 
 ### Testing / Evaluation Datasets
 
-DVLT is evaluated (and tested) on five public reconstruction benchmarks spanning indoor, outdoor, object-centric, and driving scenes. We use each benchmark's standard held-out test split as both the validation/evaluation set during development and the final testing set for the released checkpoint; no separate internal testing dataset is held out.
+DVLT is evaluated (and tested) on five public reconstruction benchmarks spanning indoor, outdoor, object-centric, and driving scenes.
 
 #### **DTU**