Back to Details

paper-planning

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Paper Planning

论文规划

A structured approach to planning academic papers before writing begins. Covers four key activities: Story design, Experiment planning, Figure design, and Timeline management.
为学术论文写作前的准备工作提供结构化方法，涵盖四大核心环节：故事设计、实验规划、图表设计和时间线管理。

When to Use This Skill

本技能适用场景

If you don't yet have an idea, use the 
research-ideation
skill first to find a problem and design a solution.
  • User wants to plan a paper before writing
  • User asks about structuring a paper's story or contributions
  • User needs to plan experiments (comparisons, ablations)
  • User wants to design pipeline figures or teaser figures
  • User asks about writing timelines or submission schedules
如果你还没有研究想法，请先使用
research-ideation
技能来寻找问题并设计解决方案。
  • 用户希望在写作前规划论文
  • 用户询问论文叙事或贡献的结构化方法
  • 用户需要规划实验（对比实验、Ablation实验）
  • 用户想要设计Pipeline图或Teaser图
  • 用户询问写作时间线或投稿日程安排

Planning Overview

规划总览

Paper planning follows four steps, ideally completed before writing begins:
Step 1: Story Design     → What is the narrative? What are the contributions?
Step 2: Experiment Plan   → What experiments prove our claims?
Step 3: Figure Design     → How do we visually communicate the method?
Step 4: Timeline          → When does each section get written?
论文规划遵循四个步骤，理想情况下应在开始写作前完成：
步骤1：故事设计 → 核心叙事是什么？研究贡献有哪些？
步骤2：实验规划 → 哪些实验能支撑我们的主张？
步骤3：图表设计 → 如何通过视觉方式呈现研究方法？
步骤4：时间线规划 → 各部分内容的写作节点是什么？

Counterintuitive Planning First

反常识规划优先原则

Prioritize these counterintuitive rules before regular planning:
  1. Write your rejection letter first: Draft the top-5 likely rejection comments ("limited novelty", "missing baseline", "not robust", etc.), then plan experiments that directly preempt each one.
  2. Narrow claim before broad claim: Define the smallest defensible core claim first. Expand only after evidence is strong. Over-broad claims fail review more often than narrow strong claims.
  3. Design ablations before polishing method text: If a module cannot be ablated cleanly, its contribution claim is weak.
  4. Allocate compute to stress tests, not only benchmarks: A single convincing stress-test figure often contributes more than multiple small benchmark gains.
  5. Plan a fallback narrative now: If SOTA gain is marginal, predefine a secondary value proposition (efficiency, robustness, fewer assumptions, wider applicability).
See references/counterintuitive-planning.md
在常规规划前，先遵循这些反常识规则：
  1. 先撰写拒稿信：草拟5条最可能出现的拒稿意见（如“创新性不足”“缺少基线对比”“鲁棒性欠佳”等），然后规划能直接规避这些问题的实验。
  2. 先精准主张再拓展：先确立最小且可辩护的核心主张，仅当证据充分后再进行拓展。过于宽泛的主张比精准有力的主张更容易被拒稿。
  3. 优先设计Ablation实验再打磨方法文本：如果某个模块无法被清晰地进行Ablation验证，那么其贡献主张是站不住脚的。
  4. 将计算资源分配给压力测试而非仅基准测试：一张有说服力的压力测试图表，往往比多个微小的基准测试提升更有价值。
  5. 提前规划备选叙事：如果在SOTA（State-of-the-Art）上的提升微不足道，预先定义次要价值主张（如效率、鲁棒性、更少假设、更广泛的适用性）。
详见 references/counterintuitive-planning.md

Step 1: Story Design

步骤1：故事设计

The "story" is the logical narrative that connects the problem, insight, method, and results.
“故事”是串联问题、洞见、方法和结果的逻辑叙事线。

Reverse Engineering the Story

逆向构建叙事

Work backwards to build the story:
  1. What is the technical problem? — The specific challenge that existing methods cannot solve well
  2. What are our contributions? — The concrete technical novelties
  3. What are the benefits and new insights? — What advantages does our approach provide?
  4. How do we lead into the challenge? — How to frame the task and previous methods to naturally arrive at the challenge
Then write forward: Task → Previous methods → Challenge → Our contributions → Advantages
通过逆向推导来搭建核心叙事：
  1. 技术问题是什么？ —— 现有方法无法很好解决的具体挑战
  2. 我们的研究贡献是什么？ —— 具体的技术创新点
  3. 带来的收益和新洞见是什么？ —— 我们的方法具备哪些优势？
  4. 如何自然引出挑战？ —— 如何铺垫任务背景和现有方法，从而顺理成章地提出挑战
再正向梳理：任务 → 现有方法 → 挑战 → 我们的贡献 → 优势

Core Elements to Define

需要明确的核心要素

Before writing any section, clearly articulate:
ElementQuestionExample
TaskWhat problem does this paper address?"Real-time 3D scene reconstruction"
ChallengeWhy can't existing methods solve it well?"Cannot handle dynamic objects efficiently"
InsightWhat key observation drives our approach?"Motion patterns are temporally sparse"
ContributionWhat do we propose?"Sparse temporal attention for dynamic regions"
AdvantageWhy is our approach better?"Reduces computation while preserving quality"
在撰写任何章节前，需清晰界定以下要素：
要素问题示例
任务本文解决的具体问题是什么？"实时3D场景重建"
挑战现有方法为何无法很好解决该问题？"无法高效处理动态对象"
洞见驱动我们方法的关键观察是什么？"运动模式在时间维度上具有稀疏性"
贡献我们提出了什么方案？"针对动态区域的稀疏时间注意力机制"
优势我们的方法为何更优？"在保证效果的同时降低计算量"

Starting Point: Pipeline Figure Sketch

起始点：绘制Pipeline图草图

Start by drawing a pipeline figure sketch. This forces you to clarify the overall method before writing.
The pipeline figure sketch serves as the paper's visual backbone:
  • Draw it before writing anything
  • It reveals whether the method is clear enough to explain
  • It identifies the novel modules vs. standard components
  • It determines subsection structure for the Method section
See references/story-design.md
先绘制Pipeline图草图，这能迫使你在写作前先理清整体方法框架。
Pipeline图草图是论文的视觉核心：
  • 在撰写任何内容前完成绘制
  • 它能反映出你的方法是否足够清晰易懂
  • 能区分创新模块与标准组件
  • 决定了方法章节的子结构
详见 references/story-design.md

Step 2: Experiment Planning

步骤2：实验规划

Plan experiments before writing to avoid discovering gaps late.
在开始写作前规划实验，避免后期发现漏洞。

Two Categories of Experiments

两类核心实验

Comparison Experiments — Prove our method is better:
  • Which baseline methods to compare against?
  • Which datasets and metrics?
  • What is the evaluation protocol?
Ablation Studies — Prove each module is effective:
  • Part 1: One big table showing impact of core contributions
  • Part 2: Several small tables for design choices and hyperparameters
对比实验 —— 证明我们的方法更优：
  • 选择哪些基线方法进行对比？
  • 使用哪些数据集和指标？
  • 评估协议是什么？
Ablation实验 —— 证明每个模块的有效性：
  • 第一部分：用一张表格展示核心贡献的影响
  • 第二部分：用多张小表格展示设计选择和超参数的影响

Planning Checklist

规划检查清单

  • List all comparison baselines (recent, relevant, SOTA)
  • Define evaluation metrics (standard for the task)
  • Identify datasets (standard benchmarks + challenging demos)
  • List ablation configurations (remove each core component)
  • Plan design-choice tables (hyperparameters, input quality, alternatives)
  • Plan demo scenarios (challenging data to showcase upper limit)
See references/experiment-planning.md
  • 列出所有对比基线（近期、相关、SOTA方法）
  • 定义评估指标（符合任务标准）
  • 确定数据集（标准基准数据集 + 具有挑战性的演示数据集）
  • 列出Ablation实验配置（移除每个核心组件）
  • 规划设计选择表格（超参数、输入质量、替代方案）
  • 规划演示场景（用具有挑战性的数据展示方法上限）
详见 references/experiment-planning.md

Experiment Plan Template

实验规划模板

Use the template at assets/experiment-plan-template.md to organize your experiment plan.
使用 assets/experiment-plan-template.md 中的模板来整理你的实验规划。

Step 3: Figure Design

步骤3：图表设计

The pipeline figure is for highlighting novelty, not for making readers understand. The Method text is what makes readers understand.
Pipeline图的作用是突出创新性，而非帮助读者理解。帮助读者理解的是方法文本内容。

Pipeline Figure Principles

Pipeline图设计原则

  • Highlight novelty: The pipeline figure showcases what is new, not just the workflow
  • Differentiate from prior work: The figure must look different from previous methods
  • Novel modules stand out: If the overall pipeline is standard, zoom in on novel modules
  • Focus on clarity of the novel parts; standard components can be simplified
  • 突出创新性：Pipeline图需展示创新点，而非仅仅呈现工作流程
  • 与现有方法区分：图表必须与之前的方法有视觉差异
  • 创新模块醒目：如果整体Pipeline是标准框架，需放大展示创新模块
  • 聚焦创新部分的清晰度；标准组件可简化处理

Teaser Figure

Teaser图

The teaser (usually Figure 1) shows the key result at a glance:
  • Place it at the top of the first page
  • Should be immediately compelling
  • Reference it from the Introduction
Teaser图（通常为图1）需一眼就能展示核心结果：
  • 放置在第一页顶部
  • 需具备即时吸引力
  • 在引言中引用该图

Visual Quality Matters

视觉质量至关重要

Visual polish directly influences review outcomes. See references/figure-design.md for the full visual quality guide (pipeline figures, tables, typography)
视觉呈现的精致程度直接影响评审结果。完整的视觉质量指南（Pipeline图、表格、排版）详见 references/figure-design.md

Step 4: Timeline

步骤4：时间线规划

4-Week Countdown

4周倒计时规划

Start writing at least 1 month before the deadline.
WeekTasks
4 weeks before1. Organize story (core contribution, module motivations). 2. List comparison experiments and ablation studies. 3. Write Introduction first draft.
3 weeks before1. Finalize the pipeline figure sketch. 2. Write Method first draft (use 
\todo{}
for unsettled details). Deadline: give Introduction + Method draft to advisor.
2 weeks beforeWrite first drafts of Experiments, Abstract, Related Work.
Last weekRevise paper, polish pipeline figure and teaser, run demos.
Critical: By the end of Week 3, you must send the Introduction and Method drafts to your advisor — otherwise the advisor likely will not have enough time to finish reviewing the paper.
See references/timeline-4week.md for the detailed schedule and progress tracking template.
在截止日期前至少1个月开始写作。
时间任务
截止前4周1. 梳理核心叙事（核心贡献、模块动机）。2. 列出对比实验和Ablation实验。3. 撰写引言初稿。
截止前3周1. 最终确定Pipeline图草图。2. 撰写方法章节初稿（用
\todo{}
标记未确定的细节）。关键截止：将引言+方法初稿提交给导师。
截止前2周撰写实验、摘要、相关工作章节的初稿。
最后一周修改论文、优化Pipeline图和Teaser图、运行演示实验。
重要提醒：必须在第3周结束前将引言和方法初稿发送给导师——否则导师可能没有足够时间完成论文评审。
详细日程和进度跟踪模板详见 references/timeline-4week.md

Handoff to Writing

向写作环节过渡

When planning is complete, pass these artifacts to 
paper-writing
:
ArtifactSource StepUsed By
Story summary (task → challenge → insight → contribution → advantage)Step 1Introduction
Module Motivation Mapping tableStep 1Method subsections
Experiment plan (comparisons + ablations + demos)Step 2Experiments section
Pipeline figure sketchStep 1 / Step 3Method overview + Figure 2
Claim-to-experiment mappingStep 2Abstract, Introduction, Experiments
Fallback narrative (if planned)Counterintuitive Rule 5Introduction / Conclusion pivot
Rejection-risk tableCounterintuitive Rule 1Self-review prioritization
规划完成后，将以下成果交付给
paper-writing
技能：
成果来源步骤使用场景
叙事摘要（任务→挑战→洞见→贡献→优势）步骤1引言章节
模块动机映射表步骤1方法子章节
实验规划（对比实验+Ablation实验+演示实验）步骤2实验章节
Pipeline图草图步骤1/步骤3方法概述+图2
主张-实验映射表步骤2摘要、引言、实验章节
备选叙事（若已规划）反常识规则5引言/结论的调整
拒稿风险表反常识规则1自我评审优先级

Reference Navigation

参考文档导航

TopicReference FileWhen to Use
Story designstory-design.mdStarting a new paper
Experiment planningexperiment-planning.mdBefore running experiments
Timelinetimeline-4week.mdSetting up a writing schedule
Figure designfigure-design.mdDesigning pipeline/teaser figures
Experiment plan templateexperiment-plan-template.mdCreating a structured experiment plan
Counterintuitive strategycounterintuitive-planning.mdIncreasing acceptance odds with non-obvious planning choices
主题参考文件适用场景
故事设计story-design.md启动新论文时
实验规划experiment-planning.md开展实验前
时间线规划timeline-4week.md制定写作日程时
图表设计figure-design.md设计Pipeline/Teaser图时
实验规划模板experiment-plan-template.md整理结构化实验规划时
反常识策略counterintuitive-planning.md采用非传统规划策略提升录用率时

Handoff to Presentation

向演示环节过渡

If preparing a conference talk or slide deck, the 
academic-slides
skill guides slide creation from your planning artifacts — including translating your story design and pipeline figure into presentation structure.
如果准备会议报告或幻灯片，
academic-slides
技能可根据你的规划成果指导幻灯片制作——包括将你的故事设计和Pipeline图转化为演示结构。