~

AAAI2021/tex/experiments.tex

@@ -100,7 +100,7 @@ capacity.
 
 \begin{figure*}[t]
   \centering
-  \includegraphics[width=\textwidth]{fig/Figure9.pdf}
+  \includegraphics[width=1.8\columnwidth]{fig/Figure9.pdf}
   \caption{Accuracy of Listeners when varying $h_{size}$ from 1 to 8. Each curve
     represents an average accuracy trend from 50 repeated training, with the
     range of [$\mu - \sigma$, $\mu + \sigma$], where $\mu$ is the average

AAAI2021/tex/introduction.tex

@@ -40,7 +40,7 @@ vocabulary can express almost infinite concepts.}
 \begin{figure}[t]
   \centering
   \includegraphics[width=\columnwidth]{fig/Figure1_motivation.pdf}
-  \caption{The distribution of compositionality when training for 100 symbolic
+  \caption{The distribution of compositionality for 100 emerged symbolic
     languages without
     any induction. It can be observed that high compositional symbolic language
     seldom emerged (e.g., $<5\%$ for compositionality $>0.99$). Moreover, varying

AAAI2021/tex/relatedwork.tex

-<<<<<<< HEAD
 \section{Related works}
 \label{sec:relatedwork}
 
 \begin{table*}[b]
-=======
-\begin{table*}[htbp]
->>>>>>> 013236e0637a916d76a342113079f93be73ec3a7
   \centering
   \small
   \caption{Handcrafted inductions in related works.}

AAAI2021/tex/theory.tex

@@ -45,7 +45,7 @@ $t=\hat{t}$ if $t$ expresses the same meaning as $\hat{t}$, e.g., ``red circle''
 
 \begin{figure*}[t]
   \centering
-  \includegraphics[width=\textwidth]{fig/Figure3_The_architecture_of_agents.pdf}
+  \includegraphics[width=1.8\columnwidth]{fig/Figure3_The_architecture_of_agents.pdf}
   \caption{The architecture of agents. \emph{Left:} speaker. \emph{Right:} listener.}
   \label{fig:agents}
 \end{figure*}