fix: add caption package, fix overfull hbox, correct RoFormer author names

main.tex

@@ -9,6 +9,7 @@
 \usepackage{graphicx}
 \usepackage{hyperref}
 \usepackage{float}
+\usepackage{caption}
 \usepackage{enumitem}
 \usepackage{url}
 
@@ -101,6 +102,7 @@ with Rotary Position Embedding (RoPE)~\cite{su2024roformer}.
 \begin{table}[H]
 \centering
 \caption{Model configuration. Total: $\sim$1.2B parameters.}
+\label{tab:model_config}
 \begin{tabular}{@{}lrlr@{}}
 \toprule
 \textbf{Parameter} & \textbf{Value} & \textbf{Parameter} & \textbf{Value} \\
@@ -235,9 +237,10 @@ Without the $1/\sqrt{2L}$ factor on $\mathbf{W}_o$ and
 $\mathbf{W}_{\text{down}}$, the per-block residual variance becomes $0.689$
 instead of $0.689/L \approx 0.014$. After $L=24$ blocks:
 \begin{equation}
-\text{Without scaling: } \Var(\mathbf{x}_{24}) \approx 1 + 24 \times 0.689 = 17.5,
-\qquad
-\text{With scaling: } \Var(\mathbf{x}_{24}) \approx 1 + 24 \times 0.014 = 1.34.
+\begin{aligned}
+\text{Without scaling: } \Var(\mathbf{x}_{24}) &\approx 1 + 24 \times 0.689 = 17.5,\\
+\text{With scaling: } \Var(\mathbf{x}_{24}) &\approx 1 + 24 \times 0.014 = 1.34.
+\end{aligned}
 \end{equation}
 
 \textbf{Stage 2: Saturation.} The 17.5$\times$ inflated variance at deep
@@ -314,7 +317,7 @@ N.~Shazeer. GLU variants improve Transformer.
 \textit{arXiv:2002.05202}, 2020.
 
 \bibitem{su2024roformer}
-J.~Su, M.~Ahmed, Y.~Lu, S.~Pan, W.~Bo, Y.~Liu.
+J.~Su, A.~Murtadha, Y.~Lu, S.~Pan, B.~Wen, Y.~Liu.
 Roformer: Enhanced transformer with rotary position embedding.
 \textit{Neurocomputing}, 568:127063, 2024.