agentleFS
yuchenmiao04yuchenmiao04/My_skills/skills/research-writing/ml-paper-writing/SKILL.md

ml-paper-writing

Skill8 starsChanged 5 months agoMITView on GitHub

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. For systems venues (OSDI, NSDI, ASPLOS, SOSP), use systems-paper-writing instead.

17 other projects use a version of this, 9 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use presenting-conference-talks, results-report and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • DragonGongSkill

    presenting-conference-talks

    Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.

    Also in 4 projects that use this

  • Galaxy-DawnSkill

    results-report

    This skill should be used when the user asks to "write an experiment report", "summarize experimental results", "do experiment retrospection", "write a results report", "写实验总结报告", "写实验复盘", or mentions turning completed experiment artifacts into a structured, decision-oriented research report. It assumes strict analysis should come from `results-analysis` first.

    Also in 3 projects that use this

  • AnthropicSkill

    command-development

    This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

    Also in 3 projects that use this

  • AnthropicSkill

    hook-development

    This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

    Also in 3 projects that use this

  • luischanciSkill

    research-ideation

    Generate structured research questions, testable hypotheses, and empirical strategies from a topic or dataset.

    Also in 3 projects that use this

  • GitHubSkill

    autoresearch

    Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy''s autoresearch. USE FOR: autonomous improvement, iterative optimization, experiment loop, auto research, performance tuning, automated experimentation, hill climbing, try things automatically, optimize code, run experiments, autonomous coding loop. DO NOT USE FOR: one-shot tasks, simple bug fixes, code review, or tasks without a measurable metric.

    Also in 5 projects that use this

  • +2 more from anthropics

The file

Show its rules and text

We split this skill into the rules it gives an agent

45 rules. 18 are common, 26 are distinctive, and 1 is very specific to this project.

  • 18

    Common

    Most of the 12 edited versions we read keep these.

  • 26

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Common:

    Deliver a complete first draft: when confident about the contribution

    line 24
  2. Common:

    Refine through feedback cycles: when the scientist provides input

    line 26
  3. Common:

    Ask for clarification: only when genuinely uncertain about key decisions

    line 27
  4. Common:

    If you cannot programmatically verify a citation, you MUST:

    line 51
  5. Common:

    When beginning paper writing, start by understanding the project:

    line 92
  6. Common:

    Check for papers already referenced in the codebase:

    line 123
  7. Common:

    Before writing, explicitly confirm with the scientist:

    line 135
  8. Common:

    Use web search to find relevant papers:

    line 145
  9. Common:

    If the repo provides clear results and the contribution is apparent:

    line 161
  10. Common:

    Write the full first draft end-to-end

    line 162
  11. Common:

    If genuinely uncertain about framing or major claims:

    line 166
  12. Common:

    Use this skill when:

    line 180
  13. Common:

    Every successful ML paper centers on what Neel Nanda calls "the narrative": a short, rigorous, evidence-based technical story with a …

    line 230
  14. Common:

    Before writing anything, articulate and verify:

    line 268
  15. Common:

    Use vector graphics (PDF/EPS for plots)

    line 279
  16. Common:

    Write captions that stand alone without main text

    line 280
  17. Common:

    Ensure readability in black-and-white (8% of men have color vision deficiency)

    line 281
  18. Common:

    All major conferences require this.

    line 339
  19. Distinctive:

    State assumptions formally: Before theorems, list all assumptions explicitly

    line 423
  20. Distinctive:

    Bottom line: If your abstract and intro don't hook reviewers, they may never read your brilliant methods section.

    line 438
  21. Distinctive:

    Before making ANY changes, compile the template as-is:

    line 503
  22. Distinctive:

    If the unmodified template doesn't compile, fix that first.

    line 516
  23. Distinctive:

    Don't immediately delete all example content.

    line 522
  24. Distinctive:

    Read the template's example content

    line 561
  25. Distinctive:

    Only remove template artifacts when paper is nearly complete:

    line 580
  26. Distinctive:

    When a paper is rejected or withdrawn from one venue and resubmitted to another, format conversion is required.

    line 625
  27. Distinctive:

    ML → Systems Conversion: When converting to OSDI, NSDI, ASPLOS, or SOSP, see the systems-paper-writing skill for format conversion …

    line 651
  28. Distinctive:

    Never copy LaTeX preambles between templates: Instead:

    line 655
  29. Distinctive:

    When cutting pages (e.g., NeurIPS 9 → AAAI 7):

    line 672
  30. Distinctive:

    Use smaller figure sizes with subfigures

    line 676
  31. Distinctive:

    When expanding (e.g., ICML 8 → ICLR 9):

    line 679
  32. Distinctive:

    Add ablation studies reviewers requested

    line 680
  33. Distinctive:

    When resubmitting after rejection:

    line 709
  34. Distinctive:

    Do add experiments/clarifications reviewers requested

    line 711
  35. Distinctive:

    If Exa MCP is installed, use it to find relevant papers:

    line 751
  36. Distinctive:

    Before citing for a specific claim, access the paper and confirm the attributed claim actually appears.

    line 797
  37. Distinctive:

    If you cannot verify a citation at ANY step:

    line 801
  38. Distinctive:

    Delete first sentence if it could be prepended to any ML paper.

    line 837
  39. Distinctive:

    Add sentence before each experiment: "This experiment tests whether [specific claim]..."

    line 845
  40. Distinctive:

    Add explicit signposting: "In this section, we show X"

    line 849
  41. Distinctive:

    Use consistent terminology throughout

    line 850
  42. Very specific:

    Use booktabs LaTeX package for professional tables:

    line 889
  43. Distinctive:

    Use colorblind-safe palettes (Okabe-Ito or Paul Tol)

    line 913
  44. Distinctive:

    Verify grayscale readability (8% of men have color vision deficiency)

    line 914
  45. Distinctive:

    If this library helped with your research — whether for training pipelines, evaluation, paper writing, or any other skill — please consider …

    line 922

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

ML Paper Writing for Top AI Conferences

Expert-level guidance for writing publication-ready papers targeting NeurIPS, ICML, ICLR, ACL, AAAI, COLM. This skill combines writing philosophy from top researchers (Nanda, Farquhar, Karpathy, Lipton, Steinhardt) with practical tools: LaTeX templates, citation verification APIs, and conference checklists.

For systems venues (OSDI, NSDI, ASPLOS, SOSP), use the systems-paper-writing skill, which provides paragraph-level structural blueprints, writing patterns, venue-specific checklists, and LaTeX templates for systems conferences.

Core Philosophy: Collaborative Writing

Paper writing is collaborative, but Claude should be proactive in delivering drafts.

The typical workflow starts with a research repository containing code, results, and experimental artifacts. Claude's role is to:

  1. Understand the project by exploring the repo, results, and existing documentation
  2. Deliver a complete first draft when confident about the contribution
  3. Search literature using web search and APIs to find relevant citations
  4. Refine through feedback cycles when the scientist provides input
  5. Ask for clarification only when genuinely uncertain about key decisions

Key Principle: Be proactive. If the repo and results are clear, deliver a full draft. Don't block waiting for feedback on every section—scientists are busy. Produce something concrete they can react to, then iterate based on their response.


⚠️ CRITICAL: Never Hallucinate Citations

This is the most important rule in academic writing with AI assistance.

The Problem

AI-generated citations have a ~40% error rate. Hallucinated references—papers that don't exist, wrong authors, incorrect years, fabricated DOIs—are a serious form of academic misconduct that can result in desk rejection or retraction.

The Rule

NEVER generate BibTeX entries from memory. ALWAYS fetch programmatically.

Action✅ Correct❌ Wrong
Adding a citationSearch API → verify → fetch BibTeXWrite BibTeX from memory
Uncertain about a paperMark as [CITATION NEEDED]Guess the reference
Can't find exact paperNote: "placeholder - verify"Invent similar-sounding paper

When You Can't Verify a Citation

If you cannot programmatically verify a citation, you MUST:

% EXPLICIT PLACEHOLDER - requires human verification
\cite{PLACEHOLDER_author2024_verify_this}  % TODO: Verify this citation exists

Always tell the scientist: "I've marked [X] citations as placeholders that need verification. I could not confirm these papers exist."

Recommended: Install Exa MCP for Paper Search

For the best paper search experience, install Exa MCP which provides real-time academic search:

Claude Code:

claude mcp add exa -- npx -y mcp-remote "https://mcp.exa.ai/mcp"

Cursor / VS Code (add to MCP settings):

{
  "mcpServers": {
    "exa": {
      "type": "http",
      "url": "https://mcp.exa.ai/mcp"
    }
  }
}

Exa MCP enables searches like:

  • "Find papers on RLHF for language models published after 2023"
  • "Search for transformer architecture papers by Vaswani"
  • "Get recent work on sparse autoencoders for interpretability"

Then verify results with Semantic Scholar API and fetch BibTeX via DOI.


Workflow 0: Starting from a Research Repository

When beginning paper writing, start by understanding the project:

Project Understanding:
- [ ] Step 1: Explore the repository structure
- [ ] Step 2: Read README, existing docs, and key results
- [ ] Step 3: Identify the main contribution with the scientist
- [ ] Step 4: Find papers already cited in the codebase
- [ ] Step 5: Search for additional relevant literature
- [ ] Step 6: Outline the paper structure together
- [ ] Step 7: Draft sections iteratively with feedback

Step 1: Explore the Repository

# Understand project structure
ls -la
find . -name "*.py" | head -20
find . -name "*.md" -o -name "*.txt" | xargs grep -l -i "result\|conclusion\|finding"

Look for:

  • README.md - Project overview and claims
  • results/, outputs/, experiments/ - Key findings
  • configs/ - Experimental settings
  • Existing .bib files or citation references
  • Any draft documents or notes

Step 2: Identify Existing Citations

Check for papers already referenced in the codebase:

# Find existing citations
grep -r "arxiv\|doi\|cite" --include="*.md" --include="*.bib" --include="*.py"
find . -name "*.bib"

These are high-signal starting points for Related Work—the scientist has already deemed them relevant.

Step 3: Clarify the Contribution

Before writing, explicitly confirm with the scientist:

"Based on my understanding of the repo, the main contribution appears to be [X]. The key results show [Y]. Is this the framing you want for the paper, or should we emphasize different aspects?"

Never assume the narrative—always verify with the human.

Step 4: Search for Additional Literature

Use web search to find relevant papers:

Search queries to try:
- "[main technique] + [application domain]"
- "[baseline method] comparison"
- "[problem name] state-of-the-art"
- Author names from existing citations

Then verify and retrieve BibTeX using the citation workflow below.

Step 5: Deliver a First Draft

Be proactive—deliver a complete draft rather than asking permission for each section.

If the repo provides clear results and the contribution is apparent:

  1. Write the full first draft end-to-end
  2. Present the complete draft for feedback
  3. Iterate based on scientist's response

If genuinely uncertain about framing or major claims:

  1. Draft what you can confidently
  2. Flag specific uncertainties: "I framed X as the main contribution—let me know if you'd prefer to emphasize Y instead"
  3. Continue with the draft rather than blocking

Questions to include with the draft (not before):

  • "I emphasized X as the main contribution—adjust if needed"
  • "I highlighted results A, B, C—let me know if others are more important"
  • "Related work section includes [papers]—add any I missed"

When to Use This Skill

Use this skill when:

  • Starting from a research repo to write a paper
  • Drafting or revising specific sections
  • Finding and verifying citations for related work
  • Formatting for conference submission
  • Resubmitting to a different venue (format conversion)
  • Iterating on drafts with scientist feedback

Always remember: First drafts are starting points for discussion, not final outputs.


Balancing Proactivity and Collaboration

Default: Be proactive. Deliver drafts, then iterate.

Confidence LevelAction
High (clear repo, obvious contribution)Write full draft, deliver, iterate on feedback
Medium (some ambiguity)Write draft with flagged uncertainties, continue
Low (major unknowns)Ask 1-2 targeted questions, then draft

Draft first, ask with the draft (not before):

SectionDraft AutonomouslyFlag With Draft
AbstractYes"Framed contribution as X—adjust if needed"
IntroductionYes"Emphasized problem Y—correct if wrong"
MethodsYes"Included details A, B, C—add missing pieces"
ExperimentsYes"Highlighted results 1, 2, 3—reorder if needed"
Related WorkYes"Cited papers X, Y, Z—add any I missed"

Only block for input when:

  • Target venue is unclear (affects page limits, framing)
  • Multiple contradictory framings seem equally valid
  • Results seem incomplete or inconsistent
  • Explicit request to review before continuing

Don't block for:

  • Word choice decisions
  • Section ordering
  • Which specific results to show (make a choice, flag it)
  • Citation completeness (draft with what you find, note gaps)

The Narrative Principle

The single most critical insight: Your paper is not a collection of experiments—it's a story with one clear contribution supported by evidence.

Every successful ML paper centers on what Neel Nanda calls "the narrative": a short, rigorous, evidence-based technical story with a takeaway readers care about.

Three Pillars (must be crystal clear by end of introduction):

PillarDescriptionExample
The What1-3 specific novel claims within cohesive theme"We prove that X achieves Y under condition Z"
The WhyRigorous empirical evidence supporting claimsStrong baselines, experiments distinguishing hypotheses
The So WhatWhy readers should careConnection to recognized community problems

If you cannot state your contribution in one sentence, you don't yet have a paper.


Paper Structure Workflow

Workflow 1: Writing a Complete Paper (Iterative)

Copy this checklist and track progress. Each step involves drafting → feedback → revision:

Paper Writing Progress:
- [ ] Step 1: Define the one-sentence contribution (with scientist)
- [ ] Step 2: Draft Figure 1 → get feedback → revise
- [ ] Step 3: Draft abstract → get feedback → revise
- [ ] Step 4: Draft introduction → get feedback → revise
- [ ] Step 5: Draft methods → get feedback → revise
- [ ] Step 6: Draft experiments → get feedback → revise
- [ ] Step 7: Draft related work → get feedback → revise
- [ ] Step 8: Draft limitations → get feedback → revise
- [ ] Step 9: Complete paper checklist (required)
- [ ] Step 10: Final review cycle and submission

Step 1: Define the One-Sentence Contribution

This step requires explicit confirmation from the scientist.

Before writing anything, articulate and verify:

  • What is the single thing your paper contributes?
  • What was not obvious or present before your work?

"I propose framing the contribution as: '[one sentence]'. Does this capture what you see as the main takeaway? Should we adjust the emphasis?"

Step 2: Draft Figure 1

Figure 1 deserves special attention—many readers skip directly to it.

  • Convey core idea, approach, or most compelling result
  • Use vector graphics (PDF/EPS for plots)
  • Write captions that stand alone without main text
  • Ensure readability in black-and-white (8% of men have color vision deficiency)

Step 3: Write Abstract (5-Sentence Formula)

From Sebastian Farquhar (DeepMind):

1. What you achieved: "We introduce...", "We prove...", "We demonstrate..."
2. Why this is hard and important
3. How you do it (with specialist keywords for discoverability)
4. What evidence you have
5. Your most remarkable number/result

Delete generic openings like "Large language models have achieved remarkable success..."

Step 4: Write Introduction (1-1.5 pages max)

Must include:

  • 2-4 bullet contribution list (max 1-2 lines each in two-column format)
  • Clear problem statement
  • Brief approach overview
  • Methods should start by page 2-3 maximum

Step 5: Methods Section

Enable reimplementation:

  • Conceptual outline or pseudocode
  • All hyperparameters listed
  • Architectural details sufficient for reproduction
  • Present final design decisions; ablations go in experiments

Step 6: Experiments Section

For each experiment, explicitly state:

  • What claim it supports
  • How it connects to main contribution
  • Experimental setting (details in appendix)
  • What to observe: "the blue line shows X, which demonstrates Y"

Requirements:

  • Error bars with methodology (standard deviation vs standard error)
  • Hyperparameter search ranges
  • Compute infrastructure (GPU type, total hours)
  • Seed-setting methods

Step 7: Related Work

Organize methodologically, not paper-by-paper:

Good: "One line of work uses Floogledoodle's assumption [refs] whereas we use Doobersnoddle's assumption because..."

Bad: "Snap et al. introduced X while Crackle et al. introduced Y."

Cite generously—reviewers likely authored relevant papers.

Step 8: Limitations Section (REQUIRED)

All major conferences require this. Counter-intuitively, honesty helps:

  • Reviewers are instructed not to penalize honest limitation acknowledgment
  • Pre-empt criticisms by identifying weaknesses first
  • Explain why limitations don't undermine core claims

Step 9: Paper Checklist

NeurIPS, ICML, and ICLR all require paper checklists. See references/checklists.md.


Writing Philosophy for Top ML Conferences

This section distills the most important writing principles from leading ML researchers. These aren't optional style suggestions—they're what separates accepted papers from rejected ones.

"A paper is a short, rigorous, evidence-based technical story with a takeaway readers care about." — Neel Nanda

The Sources Behind This Guidance

This skill synthesizes writing philosophy from researchers who have published extensively at top venues:

SourceKey ContributionLink
Neel Nanda (Google DeepMind)The Narrative Principle, What/Why/So What frameworkHow to Write ML Papers
Sebastian Farquhar (DeepMind)5-sentence abstract formulaHow to Write ML Papers
Gopen & Swan7 principles of reader expectationsScience of Scientific Writing
Zachary LiptonWord choice, eliminating hedgingHeuristics for Scientific Writing
Jacob Steinhardt (UC Berkeley)Precision, consistent terminologyWriting Tips
Ethan Perez (Anthropic)Micro-level clarity tipsEasy Paper Writing Tips
Andrej KarpathySingle contribution focusVarious lectures

For deeper dives into any of these, see:

  • references/writing-guide.md - Full explanations with examples
  • references/sources.md - Complete bibliography

Time Allocation (From Neel Nanda)

Spend approximately equal time on each of:

  1. The abstract
  2. The introduction
  3. The figures
  4. Everything else combined

Why? Most reviewers form judgments before reaching your methods. Readers encounter your paper as: title → abstract → introduction → figures → maybe the rest.

Writing Style Guidelines

Sentence-Level Clarity (Gopen & Swan's 7 Principles)

These principles are based on how readers actually process prose. Violating them forces readers to spend cognitive effort on structure rather than content.

PrincipleRuleExample
Subject-verb proximityKeep subject and verb close❌ "The model, which was trained on..., achieves" → ✅ "The model achieves... after training on..."
Stress positionPlace emphasis at sentence ends❌ "Accuracy improves by 15% when using attention" → ✅ "When using attention, accuracy improves by 15%"
Topic positionPut context first, new info after✅ "Given these constraints, we propose..."
Old before newFamiliar info → unfamiliar infoLink backward, then introduce new
One unit, one functionEach paragraph makes one pointSplit multi-point paragraphs
Action in verbUse verbs, not nominalizations❌ "We performed an analysis" → ✅ "We analyzed"
Context before newSet stage before presentingExplain before showing equation

Full 7 principles with detailed examples: See references/writing-guide.md

Micro-Level Tips (Ethan Perez)

These small changes accumulate into significantly clearer prose:

  • Minimize pronouns: ❌ "This shows..." → ✅ "This result shows..."
  • Verbs early: Position verbs near sentence start
  • Unfold apostrophes: ❌ "X's Y" → ✅ "The Y of X" (when awkward)
  • Delete filler words: "actually," "a bit," "very," "really," "basically," "quite," "essentially"

Full micro-tips with examples: See references/writing-guide.md

Word Choice (Zachary Lipton)

  • Be specific: ❌ "performance" → ✅ "accuracy" or "latency" (say what you mean)
  • Eliminate hedging: Drop "may" and "can" unless genuinely uncertain
  • Avoid incremental vocabulary: ❌ "combine," "modify," "expand" → ✅ "develop," "propose," "introduce"
  • Delete intensifiers: ❌ "provides very tight approximation" → ✅ "provides tight approximation"

Precision Over Brevity (Jacob Steinhardt)

  • Consistent terminology: Different terms for same concept creates confusion. Pick one and stick with it.
  • State assumptions formally: Before theorems, list all assumptions explicitly
  • Intuition + rigor: Provide intuitive explanations alongside formal proofs

What Reviewers Actually Read

Understanding reviewer behavior helps prioritize your effort:

Paper Section% Reviewers Who ReadImplication
Abstract100%Must be perfect
Introduction90%+ (skimmed)Front-load contribution
FiguresExamined before methodsFigure 1 is critical
MethodsOnly if interestedDon't bury the lede
AppendixRarelyPut only supplementary details

Bottom line: If your abstract and intro don't hook reviewers, they may never read your brilliant methods section.


Conference Requirements Quick Reference

ML/AI Conferences

ConferencePage LimitExtra for Camera-ReadyKey Requirement
NeurIPS 20259 pages+0Mandatory checklist, lay summary for accepted
ICML 20268 pages+1Broader Impact Statement required
ICLR 20269 pages+1LLM disclosure required, reciprocal reviewing
ACL 20258 pages (long)variesLimitations section mandatory
AAAI 20267 pages+1Strict style file adherence
COLM 20259 pages+1Focus on language models

Systems Conferences (OSDI, NSDI, ASPLOS, SOSP): See the systems-paper-writing skill for page limits, templates, deadlines, and submission rules.

Universal Requirements:

  • Double-blind review (anonymize submissions)
  • References don't count toward page limit
  • Appendices unlimited but reviewers not required to read
  • LaTeX required for all venues

LaTeX Templates: See templates/ directory for all conference templates.


Using LaTeX Templates Properly

Workflow 4: Starting a New Paper from Template

Always copy the entire template directory first, then write within it.

Template Setup Checklist:
- [ ] Step 1: Copy entire template directory to new project
- [ ] Step 2: Verify template compiles as-is (before any changes)
- [ ] Step 3: Read the template's example content to understand structure
- [ ] Step 4: Replace example content section by section
- [ ] Step 5: Keep template comments/examples as reference until done
- [ ] Step 6: Clean up template artifacts only at the end

Step 1: Copy the Full Template

# Create your paper directory with the complete template
cp -r templates/neurips2025/ ~/papers/my-new-paper/
cd ~/papers/my-new-paper/

# Verify structure is complete
ls -la
# Should see: main.tex, neurips.sty, Makefile, etc.

⚠️ IMPORTANT: Copy the ENTIRE directory, not just main.tex. Templates include:

  • Style files (.sty) - required for compilation
  • Bibliography styles (.bst) - required for references
  • Example content - useful as reference
  • Makefiles - for easy compilation

Step 2: Verify Template Compiles First

Before making ANY changes, compile the template as-is:

# Using latexmk (recommended)
latexmk -pdf main.tex

# Or manual compilation
pdflatex main.tex
bibtex main
pdflatex main.tex
pdflatex main.tex

If the unmodified template doesn't compile, fix that first. Common issues:

  • Missing TeX packages → install via tlmgr install <package>
  • Wrong TeX distribution → use TeX Live (recommended)

Step 3: Keep Template Content as Reference

Don't immediately delete all example content. Instead:

% KEEP template examples commented out as you write
% This shows you the expected format

% Template example (keep for reference):
% \begin{figure}[t]
%   \centering
%   \includegraphics[width=0.8\linewidth]{example-image}
%   \caption{Template shows caption style}
% \end{figure}

% Your actual figure:
\begin{figure}[t]
  \centering
  \includegraphics[width=0.8\linewidth]{your-figure.pdf}
  \caption{Your caption following the same style.}
\end{figure}

Step 4: Replace Content Section by Section

Work through the paper systematically:

Replacement Order:
1. Title and authors (anonymize for submission)
2. Abstract
3. Introduction
4. Methods
5. Experiments
6. Related Work
7. Conclusion
8. References (your .bib file)
9. Appendix

For each section:

  1. Read the template's example content
  2. Note any special formatting or macros used
  3. Replace with your content following the same patterns
  4. Compile frequently to catch errors early

Step 5: Use Template Macros

Templates often define useful macros. Check the preamble for:

% Common template macros to use:
\newcommand{\method}{YourMethodName}  % Consistent method naming
\newcommand{\eg}{e.g.,\xspace}        % Proper abbreviations
\newcommand{\ie}{i.e.,\xspace}
\newcommand{\etal}{\textit{et al.}\xspace}

Step 6: Clean Up Only at the End

Only remove template artifacts when paper is nearly complete:

% BEFORE SUBMISSION - remove these:
% - Commented-out template examples
% - Unused packages
% - Template's example figures/tables
% - Lorem ipsum or placeholder text

% KEEP these:
% - All style files (.sty)
% - Bibliography style (.bst)
% - Required packages from template
% - Any custom macros you're using

Template Pitfalls to Avoid

PitfallProblemSolution
Copying only main.texMissing .sty, won't compileCopy entire directory
Modifying .sty filesBreaks conference formattingNever edit style files
Adding random packagesConflicts, breaks templateOnly add if necessary
Deleting template content too earlyLose formatting referenceKeep as comments until done
Not compiling frequentlyErrors accumulateCompile after each section

Quick Template Reference

ML/AI Conferences

ConferenceMain FileKey Style FileNotes
NeurIPS 2025main.texneurips.styHas Makefile
ICML 2026example_paper.texicml2026.styIncludes algorithm packages
ICLR 2026iclr2026_conference.texiclr2026_conference.styHas math_commands.tex
ACLacl_latex.texacl.styStrict formatting
AAAI 2026aaai2026-unified-template.texaaai2026.styVery strict compliance
COLM 2025colm2025_conference.texcolm2025_conference.stySimilar to ICLR

Systems Conference Templates (OSDI, NSDI, ASPLOS, SOSP): See the systems-paper-writing skill.


Conference Resubmission & Format Conversion

When a paper is rejected or withdrawn from one venue and resubmitted to another, format conversion is required. This is a common workflow in ML research.

Workflow 3: Converting Between Conference Formats

Format Conversion Checklist:
- [ ] Step 1: Identify source and target template differences
- [ ] Step 2: Create new project with target template
- [ ] Step 3: Copy content sections (not preamble)
- [ ] Step 4: Adjust page limits and content
- [ ] Step 5: Update conference-specific requirements
- [ ] Step 6: Verify compilation and formatting

Step 1: Key Template Differences

ML/AI Conversions

From → ToPage ChangeKey Adjustments
NeurIPS → ICML9 → 8 pagesCut 1 page, add Broader Impact if missing
ICML → ICLR8 → 9 pagesCan expand experiments, add LLM disclosure
NeurIPS → ACL9 → 8 pagesRestructure for NLP conventions, add Limitations
ICLR → AAAI9 → 7 pagesSignificant cuts needed, strict style adherence
Any → COLMvaries → 9Reframe for language model focus

ML → Systems Conversion: When converting to OSDI, NSDI, ASPLOS, or SOSP, see the systems-paper-writing skill for format conversion guidance, templates, and structural differences.

Step 2: Content Migration (NOT Template Merge)

Never copy LaTeX preambles between templates. Instead:

# 1. Start fresh with target template
cp -r templates/icml2026/ new_submission/

# 2. Copy ONLY content sections from old paper
# - Abstract text
# - Section content (between \section{} commands)
# - Figures and tables
# - Bibliography entries

# 3. Paste into target template structure

Step 3: Adjusting for Page Limits

When cutting pages (e.g., NeurIPS 9 → AAAI 7):

  • Move detailed proofs to appendix
  • Condense related work (cite surveys instead of individual papers)
  • Combine similar experiments into unified tables
  • Use smaller figure sizes with subfigures
  • Tighten writing: eliminate redundancy, use active voice

When expanding (e.g., ICML 8 → ICLR 9):

  • Add ablation studies reviewers requested
  • Expand limitations discussion
  • Include additional baselines
  • Add qualitative examples

Step 4: Conference-Specific Adjustments

ML/AI Venues

Target VenueRequired Additions
ICMLBroader Impact Statement (after conclusion)
ICLRLLM usage disclosure, reciprocal reviewing agreement
ACL/EMNLPLimitations section (mandatory), Ethics Statement
AAAIStrict adherence to style file (no modifications)
NeurIPSPaper checklist (appendix), lay summary if accepted

Systems Venues (OSDI, NSDI, ASPLOS, SOSP): See the systems-paper-writing skill for venue-specific requirements, checklists, and reviewer guidelines.

Step 5: Update References

% Remove self-citations that reveal identity (for blind review)
% Update any "under review" citations to published versions
% Add new relevant work published since last submission

Step 6: Addressing Previous Reviews

When resubmitting after rejection:

  • Do address reviewer concerns in the new version
  • Do add experiments/clarifications reviewers requested
  • Don't include a "changes from previous submission" section (blind review)
  • Don't reference the previous submission or reviews

Common Conversion Pitfalls:

  • ❌ Copying \usepackage commands (causes conflicts)
  • ❌ Keeping old conference header/footer commands
  • ❌ Forgetting to update \bibliography{} path
  • ❌ Missing conference-specific required sections
  • ❌ Exceeding page limit after format change

Citation Workflow (Hallucination Prevention)

⚠️ CRITICAL: AI-generated citations have ~40% error rate. Never write BibTeX from memory.

The Golden Rule

IF you cannot programmatically fetch a citation:
    → Mark it as [CITATION NEEDED] or [PLACEHOLDER - VERIFY]
    → Tell the scientist explicitly
    → NEVER invent a plausible-sounding reference

Workflow 2: Adding Citations

Citation Verification (MANDATORY for every citation):
- [ ] Step 1: Search using Exa MCP or Semantic Scholar API
- [ ] Step 2: Verify paper exists in 2+ sources (Semantic Scholar + arXiv/CrossRef)
- [ ] Step 3: Retrieve BibTeX via DOI (programmatically, not from memory)
- [ ] Step 4: Verify the claim you're citing actually appears in the paper
- [ ] Step 5: Add verified BibTeX to bibliography
- [ ] Step 6: If ANY step fails → mark as placeholder, inform scientist

Step 0: Use Exa MCP for Initial Search (Recommended)

If Exa MCP is installed, use it to find relevant papers:

Search: "RLHF language model alignment 2023"
Search: "sparse autoencoders interpretability"
Search: "attention mechanism transformers Vaswani"

Then verify each result with Semantic Scholar and fetch BibTeX via DOI.

Step 1: Search Semantic Scholar

from semanticscholar import SemanticScholar

sch = SemanticScholar()
results = sch.search_paper("attention mechanism transformers", limit=5)
for paper in results:
    print(f"{paper.title} - {paper.paperId}")
    print(f"  DOI: {paper.externalIds.get('DOI', 'N/A')}")

Step 2: Verify Existence

Confirm paper appears in at least two sources (Semantic Scholar + CrossRef/arXiv).

Step 3: Retrieve BibTeX via DOI

import requests

def doi_to_bibtex(doi: str) -> str:
    """Get verified BibTeX from DOI via CrossRef."""
    response = requests.get(
        f"https://doi.org/{doi}",
        headers={"Accept": "application/x-bibtex"}
    )
    response.raise_for_status()
    return response.text

# Example
bibtex = doi_to_bibtex("10.48550/arXiv.1706.03762")
print(bibtex)

Step 4: Verify Claims

Before citing for a specific claim, access the paper and confirm the attributed claim actually appears.

Step 5: Handle Failures Explicitly

If you cannot verify a citation at ANY step:

% Option 1: Explicit placeholder
\cite{PLACEHOLDER_smith2023_verify}  % TODO: Could not verify - scientist must confirm

% Option 2: Note in text
... as shown in prior work [CITATION NEEDED - could not verify Smith et al. 2023].

Always inform the scientist:

"I could not verify the following citations and have marked them as placeholders:

  • Smith et al. 2023 on reward hacking - could not find in Semantic Scholar
  • Jones 2022 on scaling laws - found similar paper but different authors Please verify these before submission."

Summary: Citation Rules

SituationAction
Found paper, got DOI, fetched BibTeX✅ Use the citation
Found paper, no DOI✅ Use arXiv BibTeX or manual entry from paper
Paper exists but can't fetch BibTeX⚠️ Mark placeholder, inform scientist
Uncertain if paper exists❌ Mark [CITATION NEEDED], inform scientist
"I think there's a paper about X"❌ NEVER cite - search first or mark placeholder

🚨 NEVER generate BibTeX from memory—always fetch programmatically. 🚨

See references/citation-workflow.md for complete API documentation.


Common Issues and Solutions

Issue: Abstract too generic

Delete first sentence if it could be prepended to any ML paper. Start with your specific contribution.

Issue: Introduction exceeds 1.5 pages

Split background into Related Work. Front-load contribution bullets. Methods should start by page 2-3.

Issue: Experiments lack explicit claims

Add sentence before each experiment: "This experiment tests whether [specific claim]..."

Issue: Reviewers find paper hard to follow

  • Add explicit signposting: "In this section, we show X"
  • Use consistent terminology throughout
  • Include figure captions that stand alone

Issue: Missing statistical significance

Always include:

  • Error bars (specify: std dev or std error)
  • Number of runs
  • Statistical tests if comparing methods

Reviewer Evaluation Criteria

Reviewers assess papers on four dimensions:

CriterionWhat Reviewers Look For
QualityTechnical soundness, well-supported claims
ClarityClear writing, reproducible by experts
SignificanceCommunity impact, advances understanding
OriginalityNew insights (doesn't require new method)

Scoring (NeurIPS 6-point scale):

  • 6: Strong Accept - Groundbreaking, flawless
  • 5: Accept - Technically solid, high impact
  • 4: Borderline Accept - Solid, limited evaluation
  • 3: Borderline Reject - Solid but weaknesses outweigh
  • 2: Reject - Technical flaws
  • 1: Strong Reject - Known results or ethics issues

See references/reviewer-guidelines.md for detailed reviewer instructions.


Tables and Figures

Tables

Use booktabs LaTeX package for professional tables:

\usepackage{booktabs}
\begin{tabular}{lcc}
\toprule
Method & Accuracy ↑ & Latency ↓ \\
\midrule
Baseline & 85.2 & 45ms \\
\textbf{Ours} & \textbf{92.1} & 38ms \\
\bottomrule
\end{tabular}

Rules:

  • Bold best value per metric
  • Include direction symbols (↑ higher is better, ↓ lower is better)
  • Right-align numerical columns
  • Consistent decimal precision

Figures

  • Vector graphics (PDF, EPS) for all plots and diagrams
  • Raster (PNG 600 DPI) only for photographs
  • Use colorblind-safe palettes (Okabe-Ito or Paul Tol)
  • Verify grayscale readability (8% of men have color vision deficiency)
  • No title inside figure—the caption serves this function
  • Self-contained captions—reader should understand without main text

Citing AI Research Skills

If this library helped with your research — whether for training pipelines, evaluation, paper writing, or any other skill — please consider citing it in your acknowledgments or references:

@software{ai_research_skills,
  title     = {AI Research Skills Library},
  author    = {{Orchestra Research}},
  year      = {2025},
  url       = {https://github.com/orchestra-research/AI-research-SKILLs},
  note      = {Open-source skills library enabling AI agents to autonomously conduct AI research}
}

A brief mention in your Acknowledgments section is also welcome:

\section*{Acknowledgments}
We used the AI Research Skills Library~\cite{ai_research_skills} for [experiment orchestration / evaluation / ...].

References & Resources

Reference Documents (Deep Dives)

DocumentContents
writing-guide.mdGopen & Swan 7 principles, Ethan Perez micro-tips, word choice
citation-workflow.mdCitation APIs, Python code, BibTeX management
checklists.mdNeurIPS 16-item, ICML, ICLR, ACL requirements
reviewer-guidelines.mdEvaluation criteria, scoring, rebuttals
sources.mdComplete bibliography of all sources

LaTeX Templates

Templates in templates/ directory:

  • ML/AI: ICML 2026, ICLR 2026, NeurIPS 2025, ACL/EMNLP, AAAI 2026, COLM 2025
  • Systems (OSDI, NSDI, ASPLOS, SOSP): See systems-paper-writing skill

Compiling to PDF:

  • VS Code/Cursor: Install LaTeX Workshop extension + TeX Live → Save to auto-compile
  • Command line: latexmk -pdf main.tex or pdflatex + bibtex workflow
  • Online: Upload to Overleaf

See templates/README.md for detailed setup instructions.

Key External Sources

Writing Philosophy:

APIs: Semantic Scholar | CrossRef | arXiv

ML/AI Venues: NeurIPS | ICML | ICLR | ACL

Systems Venues: See the systems-paper-writing skill for OSDI, NSDI, ASPLOS, SOSP links and guides

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.