Fix RBF time-bias initialization

backbones.py

@@ -111,7 +111,10 @@ class TemporalAttention(nn.Module):
 
         # Layer-specific projection from shared RBF basis activations to per-head attention bias.
         self.rbf_proj = nn.Linear(n_rbf_bases, n_head, bias=False)
-        self.time_bias_scale = nn.Parameter(torch.tensor(0.0))
+        # Keep the initial RBF attention bias exactly zero through the
+        # zero-initialized projection, while leaving that projection with a
+        # live gradient from the first optimization step.
+        self.time_bias_scale = nn.Parameter(torch.tensor(1.0))
 
         self.resid_drop = nn.Dropout(dropout)
         self.reset_parameters()