diff --git a/docs/api/models/pyhealth.models.GNN.rst b/docs/api/models/pyhealth.models.GNN.rst
index d7e08a9fd..7befca0e5 100644
--- a/docs/api/models/pyhealth.models.GNN.rst
+++ b/docs/api/models/pyhealth.models.GNN.rst
@@ -3,6 +3,17 @@
 
 The GNN model (pyhealth trainer does not apply to GNN, refer to the example/ChestXray-image-generation-GAN.ipynb for examples of using GNN model).
 
+.. note::
+
+   ``pyhealth.models.gnn`` no longer seeds the global ``torch``/``numpy``
+   RNGs at import time. Previously, ``torch.manual_seed(3)`` and
+   ``np.random.seed(1)`` ran as module-level statements, so simply
+   importing ``pyhealth.models`` (which imports this module) would
+   silently overwrite any seed the caller had already set, regardless of
+   whether GCN/GAT were ever used. If you need reproducible GCN/GAT
+   weight initialization, seed explicitly right before constructing the
+   model instead.
+
 .. autoclass:: pyhealth.models.GAT
     :members:
     :undoc-members:
diff --git a/examples/gcn_mimic4.ipynb b/examples/gcn_mimic4.ipynb
index e38ee941e..de0ff9e1c 100644
--- a/examples/gcn_mimic4.ipynb
+++ b/examples/gcn_mimic4.ipynb
@@ -6,7 +6,7 @@
    "metadata": {},
    "source": [
     "# 1. Environment Setup\n",
-    "Use this section to configure deterministic behaviour and import the libraries required for the rest of the tutorial."
+    "Use this section to configure deterministic behaviour and import the libraries required for the rest of the tutorial.\n\n**Note:** earlier pyhealth versions had pyhealth.models.gnn call torch.manual_seed(3) / np.random.seed(1) at import time, so ``from pyhealth.models import GCN`` below would have silently overwritten the SEED = 42 set in this cell. This has been fixed: importing pyhealth.models no longer touches global RNG state, so the seeding above is respected."
    ]
   },
   {
@@ -139,7 +139,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Generating samples for MortalityPredictionMIMIC4 with 1 worker: 100%|██████████| 100/100 [00:00<00:00, 133.76it/s]"
+      "Generating samples for MortalityPredictionMIMIC4 with 1 worker: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 100/100 [00:00<00:00, 133.76it/s]"
      ]
     },
     {
@@ -154,7 +154,7 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "Processing samples: 100%|██████████| 108/108 [00:00<00:00, 34584.27it/s]"
+      "Processing samples: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 108/108 [00:00<00:00, 34584.27it/s]"
      ]
     },
     {
@@ -450,7 +450,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Epoch 0 / 5: 100%|██████████| 3/3 [00:00<00:00,  5.11it/s]"
+      "Epoch 0 / 5: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 3/3 [00:00<00:00,  5.11it/s]"
      ]
     },
     {
@@ -466,7 +466,7 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "Evaluation: 100%|██████████| 1/1 [00:00<00:00, 609.46it/s]"
+      "Evaluation: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 1/1 [00:00<00:00, 609.46it/s]"
      ]
     },
     {
@@ -485,7 +485,7 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "Epoch 1 / 5: 100%|██████████| 3/3 [00:00<00:00, 250.36it/s]"
+      "Epoch 1 / 5: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 3/3 [00:00<00:00, 250.36it/s]"
      ]
     },
     {
@@ -501,7 +501,7 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "Evaluation: 100%|██████████| 1/1 [00:00<00:00, 655.67it/s]"
+      "Evaluation: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 1/1 [00:00<00:00, 655.67it/s]"
      ]
     },
     {
@@ -519,7 +519,7 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "Epoch 2 / 5: 100%|██████████| 3/3 [00:00<00:00, 285.02it/s]"
+      "Epoch 2 / 5: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 3/3 [00:00<00:00, 285.02it/s]"
      ]
     },
     {
@@ -535,7 +535,7 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "Evaluation: 100%|██████████| 1/1 [00:00<00:00, 684.00it/s]"
+      "Evaluation: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 1/1 [00:00<00:00, 684.00it/s]"
      ]
     },
     {
@@ -553,7 +553,7 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "Epoch 3 / 5: 100%|██████████| 3/3 [00:00<00:00, 285.06it/s]"
+      "Epoch 3 / 5: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 3/3 [00:00<00:00, 285.06it/s]"
      ]
     },
     {
@@ -569,7 +569,7 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "Evaluation: 100%|██████████| 1/1 [00:00<00:00, 727.67it/s]"
+      "Evaluation: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 1/1 [00:00<00:00, 727.67it/s]"
      ]
     },
     {
@@ -587,7 +587,7 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "Epoch 4 / 5: 100%|██████████| 3/3 [00:00<00:00, 332.15it/s]"
+      "Epoch 4 / 5: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 3/3 [00:00<00:00, 332.15it/s]"
      ]
     },
     {
@@ -603,7 +603,7 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "Evaluation: 100%|██████████| 1/1 [00:00<00:00, 623.32it/s]"
+      "Evaluation: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 1/1 [00:00<00:00, 623.32it/s]"
      ]
     },
     {
@@ -651,7 +651,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Evaluation: 100%|██████████| 1/1 [00:00<00:00, 613.74it/s]\n"
+      "Evaluation: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 1/1 [00:00<00:00, 613.74it/s]\n"
      ]
     },
     {
@@ -665,7 +665,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Evaluation: 100%|██████████| 1/1 [00:00<00:00, 581.33it/s]"
+      "Evaluation: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 1/1 [00:00<00:00, 581.33it/s]"
      ]
     },
     {
@@ -713,7 +713,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Evaluation: 100%|██████████| 1/1 [00:00<00:00, 678.58it/s]"
+      "Evaluation: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 1/1 [00:00<00:00, 678.58it/s]"
      ]
     },
     {
diff --git a/pyhealth/models/gnn.py b/pyhealth/models/gnn.py
index 9ef323cb3..ae438841e 100644
--- a/pyhealth/models/gnn.py
+++ b/pyhealth/models/gnn.py
@@ -17,9 +17,6 @@
 from pyhealth.processors import SequenceProcessor
 from pyhealth.models.embedding import EmbeddingModel
 
-torch.manual_seed(3) 
-np.random.seed(1)
-
 """Graph Neural Network models for PyHealth.
 
 This module provides implementations of Graph Convolutional Network (GCN) and
diff --git a/tests/core/test_gnn.py b/tests/core/test_gnn.py
index ef1468ca9..22e581ec7 100644
--- a/tests/core/test_gnn.py
+++ b/tests/core/test_gnn.py
@@ -1,5 +1,7 @@
 """Unit tests for GNN models (GCN and GAT)."""
 
+import subprocess
+import sys
 import unittest
 import torch
 
@@ -453,5 +455,52 @@ def test_custom_hyperparameters(self):
         self.assertIn("y_prob", ret)
 
 
+class TestImportingModelsDoesNotResetGlobalRNG(unittest.TestCase):
+    """Regression test: pyhealth/models/gnn.py used to call
+    torch.manual_seed(3) / np.random.seed(1) at module level. Since
+    pyhealth/models/__init__.py does `from .gnn import GAT, GCN`, this ran
+    as a side effect of `import pyhealth.models` -- silently overwriting
+    any seed the user had already set for their own script, regardless of
+    whether they ever used GCN/GAT. This must run in a fresh subprocess:
+    by the time any in-process test executes, pyhealth.models is already
+    imported (and cached), so the side effect already happened once for
+    the whole test session and can't be observed from within it.
+    """
+
+    def test_import_does_not_consume_or_reset_rng_state(self):
+        script = (
+            "import torch, numpy as np\n"
+            "torch.manual_seed(12345)\n"
+            "np.random.seed(54321)\n"
+            "expected_torch = torch.rand(3).tolist()\n"
+            "expected_np = np.random.rand(3).tolist()\n"
+            "torch.manual_seed(12345)\n"
+            "np.random.seed(54321)\n"
+            "import pyhealth.models\n"  # the import under test
+            "actual_torch = torch.rand(3).tolist()\n"
+            "actual_np = np.random.rand(3).tolist()\n"
+            "assert actual_torch == expected_torch, (\n"
+            "    f'importing pyhealth.models changed the torch RNG stream: '\n"
+            "    f'{actual_torch} != {expected_torch}'\n"
+            ")\n"
+            "assert actual_np == expected_np, (\n"
+            "    f'importing pyhealth.models changed the numpy RNG stream: '\n"
+            "    f'{actual_np} != {expected_np}'\n"
+            ")\n"
+            "print('RNG_UNCHANGED')\n"
+        )
+        result = subprocess.run(
+            [sys.executable, "-c", script],
+            capture_output=True,
+            text=True,
+            timeout=120,
+        )
+        self.assertEqual(
+            result.returncode, 0,
+            f"subprocess failed:\nstdout={result.stdout}\nstderr={result.stderr}",
+        )
+        self.assertIn("RNG_UNCHANGED", result.stdout)
+
+
 if __name__ == "__main__":
     unittest.main()