academic-plotting skill

Academic Plotting for ML Papers

Generate publication-quality figures for ML/AI conference papers. Two distinct workflows:

1. Diagram figures (architecture, system design, workflows, pipelines) — AI image generation via Gemini
2. Data figures (line charts, bar charts, scatter plots, heatmaps, ablations) — matplotlib/seaborn

When to Use Which Workflow

Rule of thumb: If the figure has numerical axes, use matplotlib. If the figure has boxes and arrows, use Gemini.

Step 0: Context Analysis & Extraction

The user will typically provide one of these inputs — not a ready-made specification:

Extraction Workflow

For diagrams (research context → architecture figure):

1. Read the provided context — paper section, abstract, or description paragraph
2. Identify visual entities — What are the main components/modules/stages?

• Look for: nouns that represent system parts, named modules, layers, stages
• Count them: if >8 top-level entities, consider grouping into sections

1. Identify relationships — How do components connect?

• Look for: verbs describing data flow ("sends to", "queries", "feeds into")
• Classify: data flow (solid arrow), control flow (gray), error path (dashed red)

1. Determine layout pattern:

• Sequential pipeline → left-to-right flow
• Layered architecture → horizontal bands stacked vertically
• Hub-and-spoke → central node with radiating connections
• Hierarchical → top-down tree

1. Assign colors — One accent color per logical group/layer
2. Write every label exactly — Extract exact terminology from the paper text

For data charts (results → figure):

1. Read the provided data — table, paragraph with numbers, CSV, or JSON
2. Identify dimensions:

• What is being compared? (methods, models, configurations) → categorical axis
• What is the metric? (accuracy, loss, latency, F1) → value axis
• Is there a time/step dimension? → line plot
• Are there multiple metrics? → multi-panel or grouped bars

1. Choose chart type automatically using this priority:

• Has a step/time axis → line plot
• Comparing N methods on M benchmarks → grouped bar chart
• Single ranking → horizontal bar (leaderboard)
• Correlation between two continuous variables → scatter plot
• Square matrix of values → heatmap
• Proportional breakdown → stacked bar (avoid pie charts)

1. Determine figure sizing — Single column vs full width based on data density
2. Highlight "our method" — Identify which entry is the paper's contribution and give it a distinct color

Auto-Detection Examples

Context → Diagram: "Our system has a Planner, Executor, and Verifier. Planner sends plans to Executor, Executor returns results to Verifier, Verifier feeds back to Planner on failure." → 3 entities, cycle layout, dashed feedback arrow → Workflow 1 (Gemini)

Data → Chart: "GPT-4: MMLU 86.4, HumanEval 67.0. Ours: 88.1, 71.2. Llama-3: 79.3, 62.1." → 3 methods × 2 benchmarks → Workflow 2 (grouped bar), highlight "Ours" in coral

Workflow 1: Architecture & System Diagrams (AI Image Generation)

Use Gemini 3 Pro Image Preview to generate diagrams. Choose a visual style first — this is the single biggest factor in whether the figure looks professional or generic.

Visual Styles

Pick one style per paper (all figures should be consistent):

Style A: "Sketch / 简笔画" (Hand-Drawn)

Warm, approachable, memorable. Ideal for overview figures and system introductions. Looks like a whiteboard sketch refined by a designer.

VISUAL STYLE — HAND-DRAWN SKETCH:
- Slightly irregular, hand-drawn line quality — lines wobble gently, not perfectly straight
- Rounded, soft shapes with visible pen strokes (like drawn with a thick felt-tip marker)
- Warm off-white background (#FAFAF7), NOT pure white
- Fill colors are soft watercolor-like washes: muted blue (#D6E4F0), soft peach (#F5DEB3),
  light sage (#D4E6D4), pale lavender (#E6DFF0)
- Borders are dark charcoal (#2C2C2C) with 2-3px line weight, slightly uneven
- Arrows are hand-drawn with slight curves, ending in simple open arrowheads (not filled triangles)
- Text uses a rounded sans-serif font (like Comic Neue or Architects Daughter feel)
- Small doodle-style icons inside boxes: a tiny gear ⚙ for processing, a lightbulb 💡 for ideas,
  a magnifying glass 🔍 for search — rendered as simple line drawings, NOT emoji
- Overall feel: a carefully drawn whiteboard diagram, clean but with personality
- NO clip art, NO stock icons, NO photorealistic elements

Style B: "Modern Minimal" (Clean & Bold)

Confident, authoritative. Best for method figures where precision matters.

VISUAL STYLE — MODERN MINIMAL:
- Ultra-clean geometric shapes with crisp edges
- Bold color blocks as backgrounds for sections — NOT just accent bars, but full section fills
  using desaturated tones: slate blue (#E8EDF2), warm sand (#F5F0E8), cool mint (#E8F2EE)
- Component boxes have ROUNDED CORNERS (12px radius), NO visible border — they float on
  the section background using subtle shadow (1px, 4px blur, rgba(0,0,0,0.06))
- ONE accent color per section used sparingly on key elements: Deep blue (#2563EB),
  Emerald (#059669), Amber (#D97706), Rose (#E11D48)
- Arrows are thin (1.5px), dark gray (#6B7280), with small filled circle at source
  and clean arrowhead at target — NOT thick colored arrows
- Typography: Inter or system sans-serif, title 600 weight, body 400 weight
- Labels INSIDE boxes, not beside them
- Generous whitespace — at least 24px between elements
- NO decorative elements, NO icons — let the structure speak

Style C: "Illustrated Technical" (Icon-Rich)

Engaging, explanatory. Good for tutorial-style papers and figures that need to be self-explanatory.

VISUAL STYLE — ILLUSTRATED TECHNICAL:
- Each major component has a small MEANINGFUL ICON drawn in a consistent line-art style
  (single color, 2px stroke, ~24x24px): brain icon for reasoning, database cylinder for storage,
  arrow-loop for iteration, network nodes for communication
- Components sit inside soft rounded rectangles with a LEFT COLOR STRIP (4px wide)
- Background is pure white, but each logical group has a very faint colored region behind it
  (#F8FAFC for blue group, #FFF8F0 for orange group)
- Connections use CURVED bezier paths (not straight lines), colored by SOURCE component
- Key data flows are THICKER (3px) than secondary flows (1px, dashed)
- Small annotation badges on arrows: "×N" for repeated operations, "optional" in italics
- Title labels are ABOVE each section in small caps, letter-spaced
- Overall: like a well-designed API documentation diagram

Style D: "Accent Bar" (Classic Academic)

The default academic style. Safe for any venue, works well in grayscale.

VISUAL STYLE — CLASSIC ACCENT BAR:
- Horizontal section bands stacked vertically, pale gray (#F7F7F5) fill
- Thick colored LEFT ACCENT BAR (8px) distinguishes each section
- Content boxes: white fill, thin #DDD border, 4px rounded corners
- Section palette: Blue #4A90D9, Teal #5BA58B, Amber #D4A252, Slate #7B8794
- Sans-serif typography (Helvetica/Arial), bold titles, regular body
- Colored arrows match their SOURCE section
- Clean, flat, zero decoration

Curated Color Palettes

"Ocean Dusk" (professional, calming — default recommendation): #264653 deep teal, #2A9D8F teal, #E9C46A gold, #F4A261 sandy orange, #E76F51 burnt coral

"Ink & Wash" (for 简笔画 style): #2C2C2C charcoal ink, #D6E4F0 washed blue, #F5DEB3 washed wheat, #D4E6D4 washed sage, #E6DFF0 washed lavender

"Nord" (for modern minimal): #2E3440 polar night, #5E81AC frost blue, #A3BE8C aurora green, #EBCB8B aurora yellow, #BF616A aurora red

"Okabe-Ito" (universal colorblind-safe, required for data charts): #E69F00 orange, #56B4E9 sky blue, #009E73 green, #F0E442 yellow, #0072B2 blue, #D55E00 vermillion, #CC79A7 pink

Checklist

• [ ] Extract from context: Read paper/description, identify entities and relationships
• [ ] Choose visual style (A/B/C/D) — match the paper's tone and venue
• [ ] Choose color palette — or use one consistent with existing paper figures
• [ ] Obtain Gemini API key (GEMINIAPIKEY env var)
• [ ] Write a detailed prompt: style block + layout + connections + constraints
• [ ] Generate script at figures/genfig.py, run for 3 attempts
• [ ] Review, select best, save as figures/fig_.png

Prompt Structure (6 Sections)

Every Gemini prompt must include these sections in order:

1. FRAMING (5 lines): "Create a [STYLE_NAME]-style technical diagram for a
   [VENUE] paper. The diagram should feel [ADJECTIVES]..."

2. VISUAL STYLE (20-30 lines): Copy the full style block from above (A/B/C/D).
   This is the most important section — it determines the entire visual character.

3. COLOR PALETTE (10 lines): Exact hex codes for every color used.

4. LAYOUT (50-150 lines): Every component, box, section — exact text, spatial
   arrangement, and grouping. Be exhaustively specific.

5. CONNECTIONS (30-80 lines): Every arrow individually — source, target, style,
   label, routing direction.

6. CONSTRAINTS (10 lines): What NOT to include. Adapt per style — e.g., sketch
   style allows slight irregularity but still no clip art.

Generation Script Template

#!/usr/bin/env python3
"""Generate [FIGURE_NAME] diagram using Gemini image generation."""
import os, sys, time
from google import genai

API_KEY = os.environ.get("GEMINI_API_KEY")
if not API_KEY:
    print("ERROR: Set GEMINI_API_KEY environment variable.")
    print("  Get a key at: https://aistudio.google.com/apikey")
    sys.exit(1)

MODEL = "gemini-3-pro-image-preview"
OUTPUT_DIR = os.path.dirname(os.path.abspath(__file__))
client = genai.Client(api_key=API_KEY)

PROMPT = """
[PASTE YOUR 6-SECTION PROMPT HERE]
"""

def generate_image(prompt_text, attempt_num):
    print(f"\n{'='*60}\nAttempt {attempt_num}\n{'='*60}")
    try:
        response = client.models.generate_content(
            model=MODEL,
            contents=prompt_text,
            config=genai.types.GenerateContentConfig(
                response_modalities=["IMAGE", "TEXT"],
            ),
        )
        output_path = os.path.join(OUTPUT_DIR, f"fig_NAME_attempt{attempt_num}.png")
        for part in response.candidates[0].content.parts:
            if part.inline_data:
                with open(output_path, "wb") as f:
                    f.write(part.inline_data.data)
                print(f"Saved: {output_p

Key Rules

• Always 3 attempts — quality varies significantly between runs
• Style block is mandatory — without it, Gemini defaults to generic corporate look
• Never hardcode API keys — use os.environ.get("GEMINIAPIKEY")
• Save generation scripts — reproducibility is critical
• Specify every label exactly — Gemini may misspell or rearrange text

Full prompt examples per style: See references/diagram-generation.md

Workflow 2: Data-Driven Charts (matplotlib/seaborn)

For any figure with numerical data, axes, or quantitative comparisons.

Checklist

• [ ] Extract from context: Parse results/data, identify methods, metrics, and comparison structure
• [ ] Auto-select chart type based on data dimensions (see decision guide below)
• [ ] Prepare data (CSV, dict, or inline arrays)
• [ ] Apply publication styling (fonts, colors, sizes)
• [ ] Highlight "our method" with a distinct color
• [ ] Export as both PDF (vector) and PNG (300 DPI)
• [ ] Verify LaTeX font compatibility
• [ ] Save script at figures/genfig.py