TeXpad

Academic Papers

LaTeX conference paper template

The section skeleton reviewers expect in a CS conference submission: Abstract, Keywords, Introduction with contributions, Related Work, Method, Experiments, and Conclusion. Draft the content here, then move it into the venue's class file for camera-ready.

Open in TeXpad, no signup → Download example PDF

Free · real pdfTeX in your browser · works offline · your files stay on your device

Page 1 of the Conference Paper template, compiled with pdfTeX
Page 1, compiled with pdfTeX. This is the actual output.

Who it's for

For drafting a CS-style submission fast. TeXpad doesn't imitate two-column IEEE or ACM layouts. Export the .tex and paste your sections into the official class when you're ready.

How to customize this template

  1. End the Introduction with a bulleted list of contributions. Reviewers look for it.
  2. Use Related Work to position the paper, not just list prior work: say how each line of work differs.
  3. Put the main results table in Experiments, with your method in the last row in bold.
  4. Before submission, export LaTeX source and move it into the venue template.

When it looks right, press Download PDF. To take the .tex to Overleaf or a local TeX install, choose Export → LaTeX source.

The first lines of the source

\documentclass{article}
\usepackage{amsmath}

\title{Efficient Sparse Attention Routing for Long-Context Inference}
\author{Your Name}
\date{\today}

\begin{document}
\maketitle

\begin{abstract}
We present a routing-based sparse attention mechanism for transformer inference that reduces memory bandwidth without retraining the base model. Our method achieves a 3.1x speedup on 32k-token contexts with less than 1\% accuracy degradation.
\end{abstract}

\textbf{Keywords:} sparse attention, long-context inference, transformers, efficient deep learning

\section{Introduction}
Serving transformer models over long contexts is dominated by attention cost. Prior sparsification approaches typically require retraining, which is impractical for large pretrained models. We instead propose a post-hoc routing scheme that plugs into existing checkpoints.
…

Open the full template in the editor →

Related templates

Free LaTeX tools