diff --git a/torchvision/models/mnasnet.py b/torchvision/models/mnasnet.py
index 65462154ab6..5846111ab1c 100644
--- a/torchvision/models/mnasnet.py
+++ b/torchvision/models/mnasnet.py
@@ -95,7 +95,7 @@ def _get_depths(alpha: float) -> List[int]:
 
 
 class MNASNet(torch.nn.Module):
-    """MNASNet, as described in https://arxiv.org/pdf/1807.11626.pdf. This
+    """MNASNet, as described in https://arxiv.org/abs/1807.11626. This
     implements the B1 variant of the model.
     >>> model = MNASNet(1.0, num_classes=1000)
     >>> x = torch.rand(1, 3, 224, 224)
@@ -327,7 +327,7 @@ def _mnasnet(alpha: float, weights: Optional[WeightsEnum], progress: bool, **kwa
 def mnasnet0_5(*, weights: Optional[MNASNet0_5_Weights] = None, progress: bool = True, **kwargs: Any) -> MNASNet:
     """MNASNet with depth multiplier of 0.5 from
     `MnasNet: Platform-Aware Neural Architecture Search for Mobile
-    <https://arxiv.org/pdf/1807.11626.pdf>`_ paper.
+    <https://arxiv.org/abs/1807.11626>`_ paper.
 
     Args:
         weights (:class:`~torchvision.models.MNASNet0_5_Weights`, optional): The
@@ -355,7 +355,7 @@ def mnasnet0_5(*, weights: Optional[MNASNet0_5_Weights] = None, progress: bool =
 def mnasnet0_75(*, weights: Optional[MNASNet0_75_Weights] = None, progress: bool = True, **kwargs: Any) -> MNASNet:
     """MNASNet with depth multiplier of 0.75 from
     `MnasNet: Platform-Aware Neural Architecture Search for Mobile
-    <https://arxiv.org/pdf/1807.11626.pdf>`_ paper.
+    <https://arxiv.org/abs/1807.11626>`_ paper.
 
     Args:
         weights (:class:`~torchvision.models.MNASNet0_75_Weights`, optional): The
@@ -383,7 +383,7 @@ def mnasnet0_75(*, weights: Optional[MNASNet0_75_Weights] = None, progress: bool
 def mnasnet1_0(*, weights: Optional[MNASNet1_0_Weights] = None, progress: bool = True, **kwargs: Any) -> MNASNet:
     """MNASNet with depth multiplier of 1.0 from
     `MnasNet: Platform-Aware Neural Architecture Search for Mobile
-    <https://arxiv.org/pdf/1807.11626.pdf>`_ paper.
+    <https://arxiv.org/abs/1807.11626>`_ paper.
 
     Args:
         weights (:class:`~torchvision.models.MNASNet1_0_Weights`, optional): The
@@ -411,7 +411,7 @@ def mnasnet1_0(*, weights: Optional[MNASNet1_0_Weights] = None, progress: bool =
 def mnasnet1_3(*, weights: Optional[MNASNet1_3_Weights] = None, progress: bool = True, **kwargs: Any) -> MNASNet:
     """MNASNet with depth multiplier of 1.3 from
     `MnasNet: Platform-Aware Neural Architecture Search for Mobile
-    <https://arxiv.org/pdf/1807.11626.pdf>`_ paper.
+    <https://arxiv.org/abs/1807.11626>`_ paper.
 
     Args:
         weights (:class:`~torchvision.models.MNASNet1_3_Weights`, optional): The
diff --git a/torchvision/models/resnet.py b/torchvision/models/resnet.py
index 367fc62eba9..83c0340cef7 100644
--- a/torchvision/models/resnet.py
+++ b/torchvision/models/resnet.py
@@ -682,7 +682,7 @@ class Wide_ResNet101_2_Weights(WeightsEnum):
 @register_model()
 @handle_legacy_interface(weights=("pretrained", ResNet18_Weights.IMAGENET1K_V1))
 def resnet18(*, weights: Optional[ResNet18_Weights] = None, progress: bool = True, **kwargs: Any) -> ResNet:
-    """ResNet-18 from `Deep Residual Learning for Image Recognition <https://arxiv.org/pdf/1512.03385.pdf>`__.
+    """ResNet-18 from `Deep Residual Learning for Image Recognition <https://arxiv.org/abs/1512.03385>`__.
 
     Args:
         weights (:class:`~torchvision.models.ResNet18_Weights`, optional): The
@@ -708,7 +708,7 @@ def resnet18(*, weights: Optional[ResNet18_Weights] = None, progress: bool = Tru
 @register_model()
 @handle_legacy_interface(weights=("pretrained", ResNet34_Weights.IMAGENET1K_V1))
 def resnet34(*, weights: Optional[ResNet34_Weights] = None, progress: bool = True, **kwargs: Any) -> ResNet:
-    """ResNet-34 from `Deep Residual Learning for Image Recognition <https://arxiv.org/pdf/1512.03385.pdf>`__.
+    """ResNet-34 from `Deep Residual Learning for Image Recognition <https://arxiv.org/abs/1512.03385>`__.
 
     Args:
         weights (:class:`~torchvision.models.ResNet34_Weights`, optional): The
@@ -734,7 +734,7 @@ def resnet34(*, weights: Optional[ResNet34_Weights] = None, progress: bool = Tru
 @register_model()
 @handle_legacy_interface(weights=("pretrained", ResNet50_Weights.IMAGENET1K_V1))
 def resnet50(*, weights: Optional[ResNet50_Weights] = None, progress: bool = True, **kwargs: Any) -> ResNet:
-    """ResNet-50 from `Deep Residual Learning for Image Recognition <https://arxiv.org/pdf/1512.03385.pdf>`__.
+    """ResNet-50 from `Deep Residual Learning for Image Recognition <https://arxiv.org/abs/1512.03385>`__.
 
     .. note::
        The bottleneck of TorchVision places the stride for downsampling to the second 3x3
@@ -766,7 +766,7 @@ def resnet50(*, weights: Optional[ResNet50_Weights] = None, progress: bool = Tru
 @register_model()
 @handle_legacy_interface(weights=("pretrained", ResNet101_Weights.IMAGENET1K_V1))
 def resnet101(*, weights: Optional[ResNet101_Weights] = None, progress: bool = True, **kwargs: Any) -> ResNet:
-    """ResNet-101 from `Deep Residual Learning for Image Recognition <https://arxiv.org/pdf/1512.03385.pdf>`__.
+    """ResNet-101 from `Deep Residual Learning for Image Recognition <https://arxiv.org/abs/1512.03385>`__.
 
     .. note::
        The bottleneck of TorchVision places the stride for downsampling to the second 3x3
@@ -798,7 +798,7 @@ def resnet101(*, weights: Optional[ResNet101_Weights] = None, progress: bool = T
 @register_model()
 @handle_legacy_interface(weights=("pretrained", ResNet152_Weights.IMAGENET1K_V1))
 def resnet152(*, weights: Optional[ResNet152_Weights] = None, progress: bool = True, **kwargs: Any) -> ResNet:
-    """ResNet-152 from `Deep Residual Learning for Image Recognition <https://arxiv.org/pdf/1512.03385.pdf>`__.
+    """ResNet-152 from `Deep Residual Learning for Image Recognition <https://arxiv.org/abs/1512.03385>`__.
 
     .. note::
        The bottleneck of TorchVision places the stride for downsampling to the second 3x3
diff --git a/torchvision/models/swin_transformer.py b/torchvision/models/swin_transformer.py
index df897e2b991..2035f659bfc 100644
--- a/torchvision/models/swin_transformer.py
+++ b/torchvision/models/swin_transformer.py
@@ -508,7 +508,7 @@ def forward(self, x: Tensor):
 class SwinTransformer(nn.Module):
     """
     Implements Swin Transformer from the `"Swin Transformer: Hierarchical Vision Transformer using
-    Shifted Windows" <https://arxiv.org/pdf/2103.14030>`_ paper.
+    Shifted Windows" <https://arxiv.org/abs/2103.14030>`_ paper.
     Args:
         patch_size (List[int]): Patch size.
         embed_dim (int): Patch embedding dimension.
@@ -804,7 +804,7 @@ class Swin_V2_B_Weights(WeightsEnum):
 def swin_t(*, weights: Optional[Swin_T_Weights] = None, progress: bool = True, **kwargs: Any) -> SwinTransformer:
     """
     Constructs a swin_tiny architecture from
-    `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows <https://arxiv.org/pdf/2103.14030>`_.
+    `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows <https://arxiv.org/abs/2103.14030>`_.
 
     Args:
         weights (:class:`~torchvision.models.Swin_T_Weights`, optional): The
@@ -842,7 +842,7 @@ def swin_t(*, weights: Optional[Swin_T_Weights] = None, progress: bool = True, *
 def swin_s(*, weights: Optional[Swin_S_Weights] = None, progress: bool = True, **kwargs: Any) -> SwinTransformer:
     """
     Constructs a swin_small architecture from
-    `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows <https://arxiv.org/pdf/2103.14030>`_.
+    `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows <https://arxiv.org/abs/2103.14030>`_.
 
     Args:
         weights (:class:`~torchvision.models.Swin_S_Weights`, optional): The
@@ -880,7 +880,7 @@ def swin_s(*, weights: Optional[Swin_S_Weights] = None, progress: bool = True, *
 def swin_b(*, weights: Optional[Swin_B_Weights] = None, progress: bool = True, **kwargs: Any) -> SwinTransformer:
     """
     Constructs a swin_base architecture from
-    `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows <https://arxiv.org/pdf/2103.14030>`_.
+    `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows <https://arxiv.org/abs/2103.14030>`_.
 
     Args:
         weights (:class:`~torchvision.models.Swin_B_Weights`, optional): The
@@ -918,7 +918,7 @@ def swin_b(*, weights: Optional[Swin_B_Weights] = None, progress: bool = True, *
 def swin_v2_t(*, weights: Optional[Swin_V2_T_Weights] = None, progress: bool = True, **kwargs: Any) -> SwinTransformer:
     """
     Constructs a swin_v2_tiny architecture from
-    `Swin Transformer V2: Scaling Up Capacity and Resolution <https://arxiv.org/pdf/2111.09883>`_.
+    `Swin Transformer V2: Scaling Up Capacity and Resolution <https://arxiv.org/abs/2111.09883>`_.
 
     Args:
         weights (:class:`~torchvision.models.Swin_V2_T_Weights`, optional): The
@@ -958,7 +958,7 @@ def swin_v2_t(*, weights: Optional[Swin_V2_T_Weights] = None, progress: bool = T
 def swin_v2_s(*, weights: Optional[Swin_V2_S_Weights] = None, progress: bool = True, **kwargs: Any) -> SwinTransformer:
     """
     Constructs a swin_v2_small architecture from
-    `Swin Transformer V2: Scaling Up Capacity and Resolution <https://arxiv.org/pdf/2111.09883>`_.
+    `Swin Transformer V2: Scaling Up Capacity and Resolution <https://arxiv.org/abs/2111.09883>`_.
 
     Args:
         weights (:class:`~torchvision.models.Swin_V2_S_Weights`, optional): The
@@ -998,7 +998,7 @@ def swin_v2_s(*, weights: Optional[Swin_V2_S_Weights] = None, progress: bool = T
 def swin_v2_b(*, weights: Optional[Swin_V2_B_Weights] = None, progress: bool = True, **kwargs: Any) -> SwinTransformer:
     """
     Constructs a swin_v2_base architecture from
-    `Swin Transformer V2: Scaling Up Capacity and Resolution <https://arxiv.org/pdf/2111.09883>`_.
+    `Swin Transformer V2: Scaling Up Capacity and Resolution <https://arxiv.org/abs/2111.09883>`_.
 
     Args:
         weights (:class:`~torchvision.models.Swin_V2_B_Weights`, optional): The