Buckets:
| <!-- | |
| Vendored + adapted into posterly from ARIS (Auto-claude-code-research-in-sleep), | |
| skill paper-poster-html. Origin: https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep | |
| Upstream tokenization: MIT (c) 2026 wanshuiyin -- ../LICENSES/aris-MIT.txt | |
| This is the tokenized form of posterly's own neutral template; the class names and | |
| content are posterly's own (c) 2026 Ruishuo Chen. As an adapted derivative this file | |
| ships as part of posterly under AGPL-3.0. See ../NOTICE.md. | |
| --> | |
| <!-- | |
| ============================================================ | |
| TEMPLATE: portrait_2col (ARIS fork of posterly portrait_2col_neutral) | |
| Adapted from posterly (MIT, © 2026 Ruishuo Chen) — see LICENSES/ & NOTICE.md; | |
| ARIS modifications: flat de-gradient, --fs token scale, zero-inline-style | |
| utilities, data-source/data-color-exempt contracts. | |
| CANVAS: 24in × 36in PORTRAIT (ICLR / CVPR / many workshops default) DEFAULT. | |
| CANVAS RETARGETING: change BOTH the @page `size` (one place, in the | |
| CANVAS block below) AND the .poster `width`/`height` (one place, in | |
| the .poster rule). Keep them in sync. | |
| NOTE — ICLR workshops commonly mandate a 61×91 cm PORTRAIT board | |
| (A0-ish portrait). To retarget to that: | |
| @page { size: 610mm 910mm; } /* or 61cm 91cm */ | |
| .poster { width: calc(610 * var(--u)); height: calc(910 * var(--u)); } | |
| (1 print --u = 1mm, so 610/910 u == 610/910 mm == 61×91 cm — almost | |
| identical to the shipped 24×36in default, which is why portrait is a | |
| good fit for ICLR-workshop boards.) | |
| LAYOUT: header → body 2 columns → footer | |
| (NO framework banner, NO takeaways strip — vertical space is precious) | |
| USE WHEN: venue mandates portrait orientation, sub-A0/A1 size; | |
| reader scans top-to-bottom in column 1, then jumps to column 2. | |
| HOW TO USE: | |
| 1. Copy this file to your working directory as `poster.html`. | |
| 2. Edit the DESIGN TOKENS in `:root` (or swap a tokens/*.json palette) — | |
| the token block is the ONLY place color/font-size literals may live. | |
| 3. Replace TODO content placeholders (search for "TODO"). | |
| 4. Run `python3 tools/run_gates.py poster.html` (the default driver: preflight -> style -> measure -> polish) to align columns and check style/structure. | |
| 5. Run `python3 tools/render_preview.py poster.html` to produce the PDF. | |
| STYLE CONTRACT (ARIS source gate, tools/style_check.py): | |
| - NO inline `style=` attributes anywhere in the markup. Use the utility | |
| classes (.fs-N, .mt-N, .mb-N, .w-NN, .text-secondary, .nowrap, | |
| .text-center) defined in the UTILITIES block below. | |
| Sole exceptions: the internal SVG of a `data-color-exempt="logo"` element, | |
| and a `style="width: NN%"` on a `data-source="paper"` <img> (AR width tweak). | |
| - All font-size values reference a `--fs-1..9` token (or a COMPONENTS.md | |
| predefined `calc(var(--fs-N) * k)` variant such as `.eqn--large`). | |
| - No `linear-gradient`; the only gradient allowed is the .poster radial | |
| tint (every color stop alpha ≤ 0.06). | |
| MEASURE ROLES: every layout-critical element carries `data-measure-role`. | |
| Generic measurement scripts depend on these — do not remove. | |
| ============================================================ | |
| --> | |
| <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> | |
| <title>Repro: FlashOptim — ICML 2026</title> | |
| <!-- MathJax v3 for inline equations. CDN by default; to go offline, | |
| download a MathJax v3 release into assets/mathjax/ and change the <script> | |
| `src` below to "assets/mathjax/es5/tex-svg.js". --> | |
| <script> | |
| window.MathJax = { | |
| tex: { | |
| inlineMath: [['$', '$'], ['\\(', '\\)']], | |
| displayMath: [['$$', '$$'], ['\\[', '\\]']], | |
| packages: {'[+]': ['ams']} | |
| }, | |
| svg: { fontCache: 'global' } | |
| }; | |
| </script> | |
| <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-svg.js"></script> | |
| <style> | |
| /* ========================================================= | |
| CANVAS — 24" × 36" PORTRAIT | |
| 24in × 25.4 mm/in = 609.6 mm ≈ 610 u (width) | |
| 36in × 25.4 mm/in = 914.4 mm ≈ 914 u (height) | |
| RETARGET: change @page size here AND .poster width/height below. | |
| ICLR workshop = 610mm 910mm (61×91 cm) portrait — see header note. | |
| ========================================================= */ | |
| @page { size: 24in 36in; margin: 0; } | |
| :root { | |
| /* ===== DESIGN TOKENS ===== */ | |
| /* The ONLY place color / font-size literals are allowed (style_check | |
| rule 1 + 8 locate this block by the comment pair). Override token | |
| VALUES here only — never restyle component rules with new literals. | |
| To rebrand, edit these or load a tokens/*.json palette. */ | |
| /* Primary accent (header underline, card-highlight bar, section nums, .keyword) */ | |
| --accent: #D82E1C; | |
| --accent-deep: #972014; | |
| --accent-light: #FBEAE8; | |
| --accent-soft: #F8D9D6; | |
| /* Secondary accent for "ours / best" emphasis (table .ours row, "★" callouts) */ | |
| --gold: #AEB9C7; | |
| --gold-soft: #ECEDEF; | |
| /* Text */ | |
| --text-primary: #1A1A1A; | |
| --text-secondary: #555555; | |
| --text-muted: #888888; | |
| /* Backgrounds */ | |
| --bg-page: #F6F2F0; | |
| --bg-card: #FFFFFF; | |
| --bg-card-tint: #FAFAFB; | |
| --bg-emphasis: var(--accent-light); | |
| /* Borders */ | |
| --border-soft: #D8D8D8; | |
| --border-strong: var(--accent); | |
| /* Screen-preview backdrop only — @media print overrides body to white. | |
| Tokenized so no color literal escapes the token block (style_check rule 1). */ | |
| --bg-screen: #2b2b2b; | |
| /* Base unit. Print: 1mm; screen preview: 1.6px (~3.78px = 1mm at 96dpi). */ | |
| --u: 1.6px; | |
| /* Font-size scale (9 steps). Every font-size in this template references | |
| one of these. Off-scale px drift is forbidden (style_check rule 8); | |
| `calc(var(--fs-N) * k)` is allowed ONLY for COMPONENTS.md variants. | |
| The posterly portrait original used a few off-scale sizes (28u title, | |
| 17u section title, 14u subtitle/eqn/callout); they are snapped to the | |
| nearest scale token here so the template stays at exactly 9 steps. */ | |
| --fs-1: calc(9 * var(--u)); /* micro label */ | |
| --fs-2: calc(10 * var(--u)); /* small caption */ | |
| --fs-3: calc(11 * var(--u)); /* caption / table */ | |
| --fs-4: calc(12 * var(--u)); /* body text */ | |
| --fs-5: calc(13 * var(--u)); /* equation / emphasis */ | |
| --fs-6: calc(15 * var(--u)); /* subtitle */ | |
| --fs-7: calc(16 * var(--u)); /* section title */ | |
| --fs-8: calc(22 * var(--u)); /* banner number */ | |
| --fs-9: calc(32 * var(--u)); /* main title */ | |
| /* Fonts. Override at :root if your venue mandates a specific family. | |
| Whitelist (style_check rule 7): serif body, sans heads, mono code. */ | |
| --font-serif: "Charter", "Source Serif Pro", "Georgia", serif; | |
| --font-sans: "Inter", "Helvetica Neue", sans-serif; | |
| /* Shadows & watermark ink — tokenized so rules 1/3 stay literal-free | |
| (the faint radial page tint is the ONE allowed literal outside this | |
| block; rule 5 validates it WHEN ENABLED -- the style gate ships with rules 4-5 off). */ | |
| --shadow-screen: 0 0 60px rgba(0, 0, 0, 0.5); | |
| --shadow-card: 0 calc(2 * var(--u)) calc(6 * var(--u)) rgba(216, 46, 28, 0.05); | |
| --ornament-ink: rgba(216, 46, 28, 0.06); | |
| /* ===== END DESIGN TOKENS ===== */ | |
| } | |
| /* ========================================================= | |
| RESET + BASE | |
| ========================================================= */ | |
| * { box-sizing: border-box; margin: 0; padding: 0; } | |
| html, body { | |
| background: var(--bg-screen); | |
| font-family: var(--font-serif); | |
| color: var(--text-primary); | |
| -webkit-font-smoothing: antialiased; | |
| } | |
| /* Poster container — exact print dimensions; data-measure-role="poster" so | |
| poster_check.py can verify the canvas size. | |
| Width : 610u ≈ 24in. | |
| Height : 914u ≈ 36in. | |
| RETARGET: width/height must track @page size (see CANVAS block). */ | |
| .poster { | |
| width: calc(610 * var(--u)); | |
| height: calc(914 * var(--u)); | |
| background: var(--bg-page); | |
| /* The only gradient the catalog sanctions (rule 5 enforces it only when re-enabled): a low-alpha radial tint | |
| (every color stop alpha ≤ 0.06). NOT a linear-gradient. */ | |
| background-image: | |
| radial-gradient(ellipse at top left, rgba(216, 46, 28, 0.05), transparent 40%), | |
| radial-gradient(ellipse at bottom right, rgba(61, 74, 92, 0.05), transparent 50%); | |
| margin: 20px auto; | |
| padding: calc(10 * var(--u)) calc(12 * var(--u)); | |
| display: grid; | |
| /* header | body | footer — no banner row, no takeaways row */ | |
| grid-template-rows: auto 1fr auto; | |
| gap: calc(6 * var(--u)); | |
| box-shadow: var(--shadow-screen); | |
| position: relative; | |
| overflow: hidden; | |
| } | |
| /* Decorative top bar — flat accent (de-gradiented from posterly original). */ | |
| .poster::before { | |
| content: ""; | |
| position: absolute; top: 0; left: 0; right: 0; | |
| height: calc(8 * var(--u)); | |
| background: var(--accent); | |
| } | |
| /* ========================================================= | |
| HEADER — same 3-col structure as landscape sibling | |
| (venue badge | title-block | logo+QR), but compressed vertically | |
| by ~1u of padding since portrait is narrower. | |
| ========================================================= */ | |
| .header { | |
| display: grid; | |
| grid-template-columns: 1fr minmax(50%, auto) 1fr; /* equal side tracks (1fr) -> the title track is centred on the poster, not just between the side blocks; the centre track is floored at 50% so a one-line title still fills it (else a short title measures narrow and trips a false HEADER/TITLE-SQUEEZED). Best-effort: a side block wide enough to clamp its 1fr track can still pull the title off-centre. */ | |
| align-items: center; | |
| gap: calc(14 * var(--u)); | |
| padding: calc(1 * var(--u)) calc(3 * var(--u)) calc(4 * var(--u)); | |
| border-bottom: calc(2 * var(--u)) solid var(--accent); | |
| } | |
| .venue-badge { | |
| justify-self: start; /* anchor to the far-left edge so the centre track stays centred */ | |
| display: flex; flex-direction: column; | |
| align-items: center; justify-content: center; | |
| min-width: calc(80 * var(--u)); | |
| text-align: center; | |
| border-right: calc(1 * var(--u)) solid var(--border-soft); | |
| padding-right: calc(10 * var(--u)); | |
| } | |
| /* Portrait venue mark: snapped 28u -> --fs-9 (32u). */ | |
| .venue-badge .vb-venue { | |
| font-family: var(--font-sans); | |
| font-weight: 800; | |
| font-size: var(--fs-9); | |
| color: var(--accent-deep); | |
| line-height: 1; | |
| letter-spacing: -0.5px; | |
| } | |
| .venue-badge .vb-year { | |
| font-family: var(--font-sans); | |
| font-size: var(--fs-4); | |
| color: var(--text-secondary); | |
| margin-top: calc(3 * var(--u)); | |
| letter-spacing: 1.2px; | |
| } | |
| .venue-badge .vb-tag { | |
| font-family: var(--font-sans); | |
| font-size: var(--fs-2); | |
| color: var(--accent); | |
| font-weight: 700; | |
| margin-top: calc(2 * var(--u)); | |
| letter-spacing: 1.2px; | |
| } | |
| .title-block { text-align: center; min-width: 0; } | |
| /* Portrait title snapped 28u -> --fs-9 (32u). The reader is closer and the | |
| canvas is narrower, so the type still feels appropriately scaled. */ | |
| .title { | |
| font-family: var(--font-sans); | |
| font-weight: 800; | |
| font-size: var(--fs-9); | |
| line-height: 1.05; | |
| color: var(--accent-deep); | |
| letter-spacing: -0.5px; | |
| } | |
| .title .accent { color: var(--gold); } | |
| /* subtitle snapped 14u -> --fs-6 (15u). */ | |
| .subtitle { | |
| font-family: var(--font-sans); | |
| font-weight: 500; | |
| font-size: var(--fs-6); | |
| color: var(--text-secondary); | |
| margin-top: calc(2 * var(--u)); | |
| font-style: italic; | |
| } | |
| .authors-line { | |
| font-family: var(--font-sans); | |
| font-size: var(--fs-5); | |
| color: var(--accent); | |
| font-weight: 600; | |
| margin-top: calc(3 * var(--u)); | |
| } | |
| .authors-line .author { margin: 0 calc(4 * var(--u)); } | |
| .authors-line sup { font-size: 0.7em; color: var(--accent); } | |
| .authors-line .aff { | |
| color: var(--text-secondary); | |
| font-weight: 400; | |
| display: block; | |
| margin-top: calc(2 * var(--u)); | |
| font-size: var(--fs-3); | |
| } | |
| .right-block { | |
| justify-self: end; /* keep logo+QR in the far-right corner */ | |
| display: flex; align-items: center; | |
| gap: calc(8 * var(--u)); | |
| } | |
| .qr-block { display: flex; flex-direction: column; align-items: center; gap: calc(2 * var(--u)); } | |
| .qr-block img { | |
| width: calc(75 * var(--u)); | |
| height: calc(75 * var(--u)); | |
| border: calc(2 * var(--u)) solid var(--accent); | |
| border-radius: calc(4 * var(--u)); | |
| background: white; | |
| padding: calc(2 * var(--u)); | |
| } | |
| .qr-label { | |
| font-family: var(--font-sans); | |
| font-size: var(--fs-2); | |
| color: var(--accent); | |
| font-weight: 600; | |
| } | |
| /* Optional logo slot — drop your lab logo here. Keep rendered height ~75u to | |
| match QR; otherwise the header grows and steals vertical space. | |
| LOGO CONTRACT: a logo whose own SVG/PNG carries brand colors must be | |
| marked `data-color-exempt="logo"` so style_check exempts it from the | |
| palette / inline-style gates, e.g.: | |
| <div class="logo-slot"><img src="assets/logos/lab.png" alt="Lab" | |
| data-color-exempt="logo"></div> | |
| Inline-SVG logos carry the attribute on the <svg> element itself. */ | |
| .logo-slot img { height: calc(75 * var(--u)); width: auto; max-width: calc(300 * var(--u)); object-fit: contain; display: block; } | |
| /* Logo size classes on .logo-slot -- pick from the file's aspect ratio (SKILL.md Gate E). | |
| tall/square sit at the QR-matched slot height; wide is intentionally shorter (~68% of the | |
| QR) and width-capped so a long wordmark doesn't out-mass the title. Do NOT combine these | |
| with logo-stack (that row is width-normalized, below). */ | |
| .logo-slot.logo-tall img, | |
| .logo-slot.logo-square img { height: calc(75 * var(--u)); } | |
| .logo-slot.logo-wide img { height: calc(51 * var(--u)); max-width: calc(125 * var(--u)); } /* <22% of the ~586u portrait header */ | |
| /* Logo chip: a solid backing that keeps a transparent / edge-white logo legible on a | |
| colored/dark header (white chip) or a light header (.logo-chip-dark); the padding + radius | |
| fold a stray white box into a deliberate rounded tile (SKILL.md Gate E, Background). */ | |
| .logo-chip { | |
| display: inline-flex; align-items: center; justify-content: center; | |
| background: var(--bg-card); border-radius: calc(3 * var(--u)); | |
| padding: calc(3 * var(--u)) calc(4 * var(--u)); | |
| } | |
| .logo-chip.logo-chip-dark { background: var(--text-primary); } | |
| /* logo-row: institution logos in the header right block (REAL logos the | |
| user provided — never fabricate a seal). Each img MUST carry | |
| data-color-exempt="logo"; height pairs with the QR. */ | |
| .logo-row { display: flex; align-items: center; gap: calc(4 * var(--u)); } | |
| .logo-row img { height: calc(58 * var(--u)); width: auto; display: block; } | |
| .logo-row .lr-item { | |
| display: flex; flex-direction: column; align-items: center; | |
| gap: calc(2 * var(--u)); | |
| background: var(--bg-card); | |
| border: 1px solid var(--border-soft); | |
| border-radius: calc(3 * var(--u)); | |
| padding: calc(3 * var(--u)) calc(5 * var(--u)); | |
| } | |
| .logo-row .lr-item img { height: calc(48 * var(--u)); } | |
| .logo-row .lr-label { | |
| font-family: var(--font-sans); font-weight: 600; font-size: var(--fs-1); | |
| color: var(--text-secondary); text-align: center; line-height: 1.15; | |
| } | |
| /* logo-stack variant: WIDE WORDMARKS (AR >= ~2) normalized to EQUAL WIDTH | |
| and stacked vertically, left-aligned. Use when two wide wordmarks of | |
| different aspect ratio read unbalanced height-matched in a row (equal | |
| width lets the less-wide mark grow taller and aligns a clean block). | |
| NOT for a square seal or tall mark (equal width blows it up — keep those | |
| height-matched). Do NOT also apply the logo-wide/tall/square classes. | |
| Width stays under the LOGO/WIDE 22% cap (portrait header ~586u). */ | |
| .logo-row.logo-stack { flex-direction: column; align-items: flex-start; gap: calc(6 * var(--u)); } | |
| .logo-row.logo-stack img { width: calc(118 * var(--u)); height: auto; } | |
| /* The narrow portrait header can't fit a logo-stack BESIDE the QR (the row | |
| would blow the right-block width gate); when a stack is present, drop the | |
| right-block to a column so the logos sit ABOVE the QR. */ | |
| .right-block:has(.logo-stack) { flex-direction: column; align-items: flex-end; } | |
| /* venue badge may carry the official venue logo above its text line */ | |
| .venue-badge img { height: calc(46 * var(--u)); width: auto; display: block; margin: 0 auto calc(2 * var(--u)); } | |
| .venue-badge .vb-title { font-family: var(--font-sans); font-weight: 800; font-size: var(--fs-5); color: var(--accent-deep); letter-spacing: 0.5px; } | |
| /* ========================================================= | |
| BODY: 2 columns (portrait posters live and die on column balance) | |
| CRITICAL: Last-card bottoms of both columns must align — | |
| run poster_check.py measure poster.html — spread < 5 px required | |
| (< 3 px ideal). Gap to footer in 30–50 px. | |
| ========================================================= */ | |
| .body-grid { | |
| display: grid; | |
| grid-template-columns: 1fr 1fr; | |
| gap: calc(12 * var(--u)); | |
| /* No overflow:hidden here — it would clip card shadows (pitfall #6). | |
| .poster already clips at the page boundary; min-height:0 is the | |
| grid-blowout guard. */ | |
| min-height: 0; | |
| } | |
| .column { | |
| display: flex; flex-direction: column; | |
| gap: calc(7 * var(--u)); | |
| min-height: 0; | |
| height: 100%; | |
| padding-bottom: calc(4 * var(--u)); /* shadow breathing room above footer */ | |
| } | |
| /* ========================================================= | |
| CARDS — identical tokens to sibling | |
| ========================================================= */ | |
| .card { | |
| background: var(--bg-card); | |
| border-radius: calc(5 * var(--u)); | |
| padding: calc(5 * var(--u)) calc(10 * var(--u)); | |
| border: calc(1 * var(--u)) solid var(--border-soft); | |
| box-shadow: var(--shadow-card); | |
| position: relative; | |
| } | |
| .card.tinted { background: var(--bg-card-tint); } | |
| .card.card--compact { padding: calc(3 * var(--u)) calc(7 * var(--u)); } /* predefined variant: tighter padding (fix (f)) */ | |
| /* .highlight de-gradiented: flat emphasis tint instead of a linear-gradient. */ | |
| .card.highlight { | |
| border-left: calc(6 * var(--u)) solid var(--accent); | |
| background: var(--bg-emphasis); | |
| } | |
| /* section-title snapped 17u -> --fs-7 (16u). */ | |
| .section-title { | |
| font-family: var(--font-sans); | |
| font-weight: 700; | |
| font-size: var(--fs-7); | |
| color: var(--accent-deep); | |
| margin-bottom: calc(3 * var(--u)); | |
| display: flex; align-items: center; | |
| gap: calc(5 * var(--u)); | |
| } | |
| /* Title text + any ★ marker share ONE .st-text span, so the heading wraps as | |
| natural text (hanging indent) instead of flex-wrapping atomic items: the | |
| number badge is never stranded on its own line and the ★ never widows. */ | |
| .section-title .st-text { flex: 1; min-width: 0; line-height: 1.18; } | |
| /* Graceful fallback if a title is NOT wrapped in .st-text: float the badge so | |
| bare inline text still wraps beside it rather than dropping below it. */ | |
| .section-title:not(:has(.st-text)) { display: block; line-height: 1.18; } | |
| .section-title:not(:has(.st-text)) .num { float: left; margin-right: calc(5 * var(--u)); } | |
| .section-title .num { | |
| display: inline-flex; align-items: center; justify-content: center; | |
| width: calc(24 * var(--u)); height: calc(24 * var(--u)); | |
| background: var(--accent); color: white; | |
| border-radius: 50%; | |
| font-size: var(--fs-6); font-weight: 700; | |
| flex-shrink: 0; | |
| } | |
| /* Inline "★ key/headline" tag inside a section title (replaces inline styles). */ | |
| .section-title .tag-key { | |
| color: var(--gold); | |
| font-size: var(--fs-4); | |
| } | |
| /* Body text — snapped 13u -> --fs-5. The 2-column portrait gives each column | |
| enough width to carry a meatier line height comfortably. */ | |
| .body-text, .card p, .card li { | |
| font-family: var(--font-serif); | |
| font-size: var(--fs-5); | |
| line-height: 1.35; | |
| color: var(--text-primary); | |
| } | |
| .card ul, .card ol { padding-left: calc(20 * var(--u)); } | |
| .card li { margin-bottom: calc(2 * var(--u)); } | |
| .keyword { color: var(--accent); font-weight: 700; } | |
| .keyword-gold { color: var(--gold); font-weight: 700; } | |
| .highlight-text { | |
| background: var(--bg-emphasis); | |
| padding: 0 calc(3 * var(--u)); | |
| border-radius: calc(2 * var(--u)); | |
| } | |
| /* Equation block — snapped 14u -> --fs-5 (13u). */ | |
| .eqn { | |
| background: var(--bg-emphasis); | |
| border-left: calc(3 * var(--u)) solid var(--accent); | |
| padding: calc(4 * var(--u)) calc(10 * var(--u)); | |
| margin: calc(4 * var(--u)) 0; | |
| font-size: var(--fs-5); | |
| overflow-x: hidden; | |
| } | |
| /* COMPONENTS.md predefined variant: a larger equation when a formula is the | |
| hero of a card. The `calc(var(--fs-N) * k)` form is allowed ONLY for | |
| registered variants like this one (style_check rule 8 / §12.5 nit 1). */ | |
| .eqn--large { font-size: calc(var(--fs-5) * 1.25); } | |
| .eqn .label { | |
| display: block; | |
| font-family: var(--font-sans); | |
| font-size: var(--fs-2); | |
| color: var(--accent); | |
| font-weight: 600; | |
| margin-bottom: calc(2 * var(--u)); | |
| text-transform: uppercase; | |
| letter-spacing: 1px; | |
| } | |
| /* Callout: solid accent for primary; solid gold for theorems / "★ key" strips | |
| (gold .callout de-gradiented to a flat fill). Snapped 13u -> --fs-5. */ | |
| .callout { | |
| background: var(--accent); | |
| color: white; | |
| padding: calc(5 * var(--u)) calc(10 * var(--u)); | |
| border-radius: calc(4 * var(--u)); | |
| font-size: var(--fs-5); | |
| margin: calc(4 * var(--u)) 0; | |
| } | |
| .callout strong { color: var(--gold); } | |
| .callout.gold { | |
| background: var(--gold); | |
| color: var(--accent-deep); | |
| } | |
| .callout.gold strong { color: var(--accent-deep); } | |
| /* Figure container */ | |
| .figure { margin: calc(4 * var(--u)) 0; text-align: center; } | |
| .figure img:not([class*="w-"]) { width: 100%; } | |
| .figure--wide img { width: 100%; } /* predefined variant: force full card width over any .w-NN (fix (f)) */ | |
| .figure img { | |
| /* FIGURE CONTRACT: figures must come from the paper: | |
| <img src="assets/paper_figures/x.png" data-source="paper" | |
| data-asset-id="x" class="w-100"> | |
| data-source/data-asset-id are required by asset_check + exempt the | |
| image from style_check's palette gate. Use .w-NN utilities (not an | |
| inline width) to size it; the only inline-style exception the gate | |
| allows is `style="width: NN%"` on a data-source="paper" <img>. */ | |
| border-radius: calc(4 * var(--u)); | |
| border: calc(1 * var(--u)) solid var(--border-soft); | |
| background: white; | |
| } | |
| .figure .caption { | |
| font-family: var(--font-sans); | |
| font-size: var(--fs-3); | |
| color: var(--text-secondary); | |
| margin-top: calc(3 * var(--u)); | |
| line-height: 1.3; | |
| text-align: left; | |
| } | |
| .figure .caption strong { color: var(--accent-deep); } | |
| /* Float a figure BESIDE text in a TEXT-RICH card: text wraps to its side | |
| and then below it. The clearfix grows the card to contain the float; | |
| mark the <img> data-fig-layout="beside-text" so the AR gates honour the | |
| intentionally small width. Use ONLY when there is enough text to fill the | |
| figure's height -- a text-sparse card should center .figure instead. A | |
| short-text float leaves an L-shaped void below the text, which polish's | |
| FIG/BESIDE-TEXT-VOID flags. */ | |
| .fig-wrap::after { content: ""; display: table; clear: both; } | |
| .ff-fig { | |
| float: right; | |
| width: 48%; max-width: 58%; min-width: 38%; | |
| margin: calc(1 * var(--u)) 0 calc(3 * var(--u)) calc(11 * var(--u)); | |
| text-align: center; | |
| } | |
| .ff-fig.left { | |
| float: left; | |
| margin: calc(1 * var(--u)) calc(11 * var(--u)) calc(3 * var(--u)) 0; | |
| } | |
| .ff-fig img { | |
| display: block; | |
| width: 100%; | |
| border-radius: calc(4 * var(--u)); | |
| border: calc(1 * var(--u)) solid var(--border-soft); | |
| background: white; | |
| } | |
| .ff-fig .caption { | |
| font-family: var(--font-sans); | |
| font-size: var(--fs-3); | |
| color: var(--text-secondary); | |
| margin-top: calc(3 * var(--u)); | |
| line-height: 1.3; | |
| text-align: center; | |
| } | |
| /* Result table with .ours row highlighted gold — snapped 12u -> --fs-4. */ | |
| .result-table { | |
| width: 100%; | |
| border-collapse: collapse; | |
| font-family: var(--font-sans); | |
| font-size: var(--fs-4); | |
| margin-top: calc(3 * var(--u)); | |
| } | |
| .result-table th, .result-table td { | |
| padding: calc(2 * var(--u)) calc(4 * var(--u)); | |
| text-align: center; | |
| border-bottom: calc(1 * var(--u)) solid var(--border-soft); | |
| } | |
| .result-table thead th { | |
| background: var(--accent); color: white; | |
| font-weight: 600; font-size: var(--fs-3); | |
| } | |
| .result-table tbody tr.group-row td { | |
| background: var(--bg-emphasis); font-weight: 700; | |
| text-align: left; | |
| color: var(--accent-deep); | |
| padding-left: calc(8 * var(--u)); | |
| border-bottom: calc(2 * var(--u)) solid var(--accent); | |
| } | |
| .result-table tbody tr.ours td { background: var(--gold-soft); font-weight: 700; } | |
| .result-table tbody tr.ours td:first-child { color: var(--accent-deep); } | |
| .result-table .method { text-align: left; padding-left: calc(8 * var(--u)); } | |
| .result-table .best { color: var(--accent); font-weight: 700; } | |
| /* Muted reference row (replaces inline color styles in table cells). */ | |
| .result-table .ref, .result-table .ref td { color: var(--text-muted); } | |
| /* 3-up stat box — kb-num snapped 16u -> --fs-7. */ | |
| .keybox { | |
| display: grid; | |
| grid-template-columns: repeat(3, 1fr); | |
| gap: calc(4 * var(--u)); | |
| margin: calc(4 * var(--u)) 0 0; | |
| } | |
| .keybox .kb-item { | |
| background: var(--bg-emphasis); | |
| border-top: calc(2 * var(--u)) solid var(--accent); | |
| padding: calc(3 * var(--u)); | |
| text-align: center; | |
| /* The grid stretches every tile to the tallest one; center the content | |
| vertically so a 1-line tile's number aligns with a 2-line neighbour's | |
| instead of top-ragged (SKILL Layout pitfall — stat-tile alignment). */ | |
| display: flex; flex-direction: column; justify-content: center; | |
| border-radius: 0 0 calc(3 * var(--u)) calc(3 * var(--u)); | |
| } | |
| .kb-item .kb-num { | |
| font-family: var(--font-sans); | |
| font-weight: 800; | |
| font-size: var(--fs-7); | |
| color: var(--accent); | |
| line-height: 1; | |
| } | |
| .kb-item .kb-label { | |
| font-family: var(--font-sans); | |
| font-size: var(--fs-2); | |
| color: var(--text-secondary); | |
| margin-top: calc(2 * var(--u)); | |
| line-height: 1.15; | |
| } | |
| /* ========================================================= | |
| FOOTER — same as sibling (snapped 12u -> --fs-4). | |
| (no takeaways strip in portrait — final card per column carries | |
| takeaway content instead) | |
| ========================================================= */ | |
| .footer { | |
| grid-column: 1 / -1; | |
| display: flex; justify-content: space-between; align-items: baseline; | |
| /* Narrow portrait: when the two blocks can't sit side by side they stack | |
| (wrap) instead of overflowing; row-gap keeps the stacked blocks legible. */ | |
| flex-wrap: wrap; gap: calc(2 * var(--u)) calc(10 * var(--u)); | |
| padding-top: calc(8 * var(--u)); | |
| border-top: calc(1 * var(--u)) solid var(--border-soft); | |
| font-family: var(--font-sans); | |
| font-size: var(--fs-4); | |
| color: var(--text-muted); | |
| } | |
| /* Long repo URL / email breaks mid-token rather than overflowing the edge. */ | |
| .footer .repo { color: var(--accent); font-weight: 600; overflow-wrap: anywhere; } | |
| /* Footer method name (replaces an inline color style). */ | |
| .footer .method-name { color: var(--accent-deep); } | |
| /* Optional watermark */ | |
| .ornament { | |
| position: absolute; | |
| right: calc(18 * var(--u)); | |
| bottom: calc(18 * var(--u)); | |
| font-family: var(--font-sans); | |
| font-size: var(--fs-9); | |
| color: var(--ornament-ink); | |
| font-weight: 900; | |
| letter-spacing: 4px; | |
| pointer-events: none; | |
| user-select: none; | |
| } | |
| /* ========================================================= | |
| UTILITIES — replace inline `style=` attributes in the markup. | |
| These exist so the template body can stay 100% inline-style-free | |
| (style_check rule 2). Add new utilities here, never an inline style. | |
| ========================================================= */ | |
| /* ========================================================= | |
| DENSITY COMPONENTS (catalogued — see COMPONENTS.md). | |
| Guardrail: no component-local color semantics. Distinction is | |
| carried by labels, order and typography — never by new hues. | |
| ========================================================= */ | |
| /* equation-stack: compact multi-row formula stack (denser than one big .eqn) */ | |
| .equation-stack { margin: calc(2 * var(--u)) 0; } | |
| .equation-stack .eqn { margin: calc(2 * var(--u)) 0; padding: calc(2 * var(--u)) calc(8 * var(--u)); } | |
| /* eqn-anatomy: term-by-term anatomy grid (2x2 default; --row variant = 1x4) */ | |
| .eqn-anatomy { | |
| display: grid; grid-template-columns: 1fr 1fr; | |
| gap: calc(2.5 * var(--u)); margin: calc(3 * var(--u)) 0; | |
| } | |
| .eqn-anatomy.eqn-anatomy--row { grid-template-columns: repeat(4, 1fr); } | |
| .eqn-anatomy .ea-item { | |
| background: var(--bg-card-tint); | |
| border: 1px solid var(--border-soft); | |
| border-left: calc(2 * var(--u)) solid var(--accent); | |
| border-radius: calc(2 * var(--u)); | |
| padding: calc(2 * var(--u)) calc(4 * var(--u)); | |
| font-size: var(--fs-2); line-height: 1.3; | |
| } | |
| .eqn-anatomy .ea-tag { | |
| display: inline-block; font-family: var(--font-sans); font-weight: 700; | |
| font-size: var(--fs-1); color: var(--accent-deep); | |
| background: var(--accent-light); border-radius: calc(1.5 * var(--u)); | |
| padding: calc(0.5 * var(--u)) calc(2.5 * var(--u)); | |
| margin-right: calc(1.5 * var(--u)); | |
| } | |
| /* flow-strip: labeled pipeline, ALL steps the same accent; ONLY the | |
| final step may carry the gold top bar. Not an "algorithm" unless the | |
| paper has one — see COMPONENTS.md. */ | |
| .flow-strip { display: flex; align-items: stretch; gap: calc(1.5 * var(--u)); margin: calc(3 * var(--u)) 0; } | |
| .flow-strip .step { | |
| flex: 1; background: var(--accent-light); | |
| border: 1px solid var(--accent-soft); border-radius: calc(2 * var(--u)); | |
| padding: calc(2 * var(--u)) calc(2.5 * var(--u)); | |
| text-align: center; font-size: var(--fs-2); line-height: 1.25; | |
| } | |
| .flow-strip .step .step-name { | |
| display: block; font-family: var(--font-sans); font-weight: 700; | |
| font-size: var(--fs-1); color: var(--accent-deep); | |
| letter-spacing: 0.5px; text-transform: uppercase; | |
| margin-bottom: calc(1 * var(--u)); | |
| } | |
| .flow-strip .step--final { border-top: calc(1.5 * var(--u)) solid var(--gold); background: var(--gold-soft); } | |
| .flow-strip .arrow { | |
| align-self: center; color: var(--accent); | |
| font-family: var(--font-sans); font-weight: 700; font-size: var(--fs-4); | |
| flex: 0 0 auto; | |
| } | |
| /* figure--duo: two paper figures sharing one caption; each img MUST be | |
| a data-source="paper" asset and carry .w-45/.w-50 (42-48% each). */ | |
| .figure--duo { display: flex; gap: calc(3 * var(--u)); align-items: flex-start; justify-content: center; } | |
| .figure--duo img { max-width: 48%; min-width: 0; } /* hard cap: duo contract is 42-48% each; an oversized w-NN cannot overflow the card */ | |
| /* result-table derived column (gold-soft = DERIVED arithmetic; label it) */ | |
| .result-table th.derived, .result-table td.derived { | |
| background: var(--gold-soft); font-family: var(--font-sans); font-weight: 700; | |
| } | |
| /* keybox 4-up variant */ | |
| .keybox.keybox--4 { grid-template-columns: repeat(4, 1fr); } | |
| /* algo: compact numbered procedure — ONLY when the paper itself states | |
| an explicit algorithm/procedure; never invent steps. */ | |
| ol.algo { padding-left: calc(16 * var(--u)); } | |
| ol.algo li { margin-bottom: calc(1.5 * var(--u)); font-size: var(--fs-3); line-height: 1.3; } | |
| /* claim-pills: provenance mini-table (numeric-heavy posters only) */ | |
| .claim-pills { width: 100%; border-collapse: collapse; font-family: var(--font-sans); font-size: var(--fs-2); } | |
| .claim-pills td { | |
| border-bottom: 1px solid var(--border-soft); | |
| padding: calc(1.5 * var(--u)) calc(3 * var(--u)); | |
| } | |
| .claim-pills .cp-id { | |
| font-weight: 700; color: var(--accent-deep); background: var(--accent-light); | |
| border-radius: calc(1.5 * var(--u)); padding: 0 calc(2.5 * var(--u)); white-space: nowrap; | |
| } | |
| .claim-pills .cp-fact { color: var(--accent-deep); font-weight: 700; } | |
| .claim-pills .cp-derived { color: var(--gold); font-weight: 700; } | |
| /* Grid-blowout guards: (1) columns may shrink below min-content so a | |
| wide equation can never widen its track and squeeze siblings; | |
| (2) over-wide display math scales down to fit its box instead of | |
| blowing out the card (SVG keeps aspect via height:auto). */ | |
| .body-grid > .column { min-width: 0; } | |
| .card { min-width: 0; } | |
| .eqn mjx-container > svg { max-width: 100%; height: auto; } | |
| /* ── Utility classes — defined LAST so equal-specificity ties | |
| resolve in the utility's favor (source order). ── */ | |
| .fs-1 { font-size: var(--fs-1); } | |
| .fs-2 { font-size: var(--fs-2); } | |
| .fs-3 { font-size: var(--fs-3); } | |
| .fs-4 { font-size: var(--fs-4); } | |
| .fs-5 { font-size: var(--fs-5); } | |
| .fs-6 { font-size: var(--fs-6); } | |
| .fs-7 { font-size: var(--fs-7); } | |
| .fs-8 { font-size: var(--fs-8); } | |
| .fs-9 { font-size: var(--fs-9); } | |
| .mt-1 { margin-top: calc(1 * var(--u)); } | |
| .mt-2 { margin-top: calc(2 * var(--u)); } | |
| .mt-3 { margin-top: calc(3 * var(--u)); } | |
| .mt-4 { margin-top: calc(4 * var(--u)); } | |
| .mt-5 { margin-top: calc(5 * var(--u)); } | |
| .mt-6 { margin-top: calc(6 * var(--u)); } | |
| .mb-1 { margin-bottom: calc(1 * var(--u)); } | |
| .mb-2 { margin-bottom: calc(2 * var(--u)); } | |
| .mb-3 { margin-bottom: calc(3 * var(--u)); } | |
| .mb-4 { margin-bottom: calc(4 * var(--u)); } | |
| .pb-2 { padding-bottom: calc(2 * var(--u)); } | |
| .pb-5 { padding-bottom: calc(5 * var(--u)); } | |
| .pb-7 { padding-bottom: calc(7 * var(--u)); } | |
| .pb-8 { padding-bottom: calc(8 * var(--u)); } | |
| .pb-16 { padding-bottom: calc(16 * var(--u)); } | |
| .pb-12 { padding-bottom: calc(12 * var(--u)); } | |
| .pb-10 { padding-bottom: calc(10 * var(--u)); } | |
| /* system extension (build note): cap the title track so a long one-line | |
| title wraps balanced and stays centred against the venue badge */ | |
| .maxw-380 { max-width: calc(380 * var(--u)); justify-self: center; } | |
| .w-45 { width: 45%; } | |
| .w-50 { width: 50%; } | |
| .w-55 { width: 55%; } | |
| .w-60 { width: 60%; } | |
| .w-65 { width: 65%; } | |
| .w-70 { width: 70%; } | |
| .w-75 { width: 75%; } | |
| .w-80 { width: 80%; } | |
| .w-85 { width: 85%; } | |
| .w-90 { width: 90%; } | |
| .w-95 { width: 95%; } | |
| .w-100 { width: 100%; } | |
| .text-secondary { color: var(--text-secondary); } | |
| .text-muted { color: var(--text-muted); } | |
| .nowrap { white-space: nowrap; } | |
| .text-center { text-align: center; } | |
| /* ========================================================= | |
| PRINT OVERRIDE — KEEP LAST so it wins source-order ties. | |
| RETARGET: width/height must match @page size in the CANVAS block. | |
| ========================================================= */ | |
| @media print { | |
| html, body { background: white; } | |
| .poster { margin: 0; box-shadow: none; width: 24in; height: 36in; page-break-after: avoid; } | |
| :root { --u: 1mm; } | |
| } | |
| </style> | |
| </head> | |
| <body> | |
| <div class="poster" data-measure-role="poster"> | |
| <!-- =========================== HEADER =========================== --> | |
| <header class="header" data-measure-role="header"> | |
| <!-- LEFT: venue badge (text only; ICML 2026 is the actual venue). --> | |
| <div class="venue-badge"> | |
| <div class="vb-venue">ICML</div> | |
| <div class="vb-year">2026</div> | |
| <div class="vb-tag">REPRO</div> | |
| </div> | |
| <!-- CENTER: title block. --> | |
| <div class="title-block maxw-380"> | |
| <h1 class="title fs-8">FlashOptim: Optimizers for Memory-Efficient Training <span class="accent">[ A Reproduction ]</span></h1> | |
| <div class="subtitle">Independent CPU-only verification of the paper's mechanism claims.</div> | |
| <div class="authors-line"> | |
| <span class="author">ProCreations (Claude agent)<sup>✉</sup></span> | |
| <span class="aff">Hugging Face × AlphaXiv ICML 2026 Agent Reproduction Challenge · paper by Gonzalez Ortiz, Gupta, Rinard & Blalock (Databricks)</span> | |
| </div> | |
| </div> | |
| <!-- RIGHT: spacer to keep the title track centred (no logo/QR assets provided). --> | |
| <div class="right-block"></div> | |
| </header> | |
| <!-- ============================ BODY ============================ | |
| 2 columns. Each column should carry 4-5 cards. The last card of each | |
| column should typically be a takeaways / conclusion card so the | |
| reader exits with a clear message (we don't have a takeaways strip | |
| in portrait). | |
| ============================================================ --> | |
| <div class="body-grid" data-measure-role="body"> | |
| <!-- ============ COLUMN 1 ============ --> | |
| <div class="column" data-measure-role="column"> | |
| <div class="card highlight" data-measure-role="card" data-logbook-target="claim-6-ulp-reconstruction-error-companding-prevents-divergence" data-logbook-label="Claim 6 evidence"> | |
| <div class="section-title"><span class="num">1</span><span class="st-text">ULP Splitting <span class="tag-key">★ EXHAUSTIVE</span></span></div> | |
| <p class="body-text"> | |
| FlashOptim stores a bf16 weight plus the downcast error's position inside | |
| <span class="keyword">±ULP(θ′)/2</span> in 8 integer bits. Re-implementing Alg. 1, we swept | |
| <strong>all 4,278,190,080 finite FP32 values</strong> — the paper's Fig. 3 protocol, no sampling. | |
| </p> | |
| <div class="figure mt-3"> | |
| <img src="images/fig_fig3.svg" alt="Exhaustive FP32 reconstruction error by exponent, bf16 target" class="w-95"> | |
| <div class="caption"> | |
| BF16+INT16 mean error 3.4×10<sup>−10</sup> (<10<sup>−9</sup> claimed ✓); BF16+BF16 is 36× | |
| worse ✓. Not replicated: 99.92% bitwise-exact (we get 99.53%). | |
| </div> | |
| </div> | |
| </div> | |
| <div class="card highlight pb-16" data-measure-role="card" data-logbook-target="conclusion" data-logbook-label="Conclusion & scope"> | |
| <div class="section-title"><span class="num">2</span><span class="st-text">Verdicts & Honest Scope <span class="tag-key fs-3">★</span></span></div> | |
| <p class="body-text"> | |
| All evidence: local CPU, <span class="highlight-text">$0.00 paid</span>; GPU stages frozen | |
| by order. | |
| </p> | |
| <ul class="mt-3 fs-3"> | |
| <li><strong>1 Mechanism (§3)</strong> — verified by code audit + impl.</li> | |
| <li><strong>2 16→7 (5) B/param</strong> — verified, exact</li> | |
| <li><strong>3 8B peak −36%</strong> — components exact; peak unavailable</li> | |
| <li><strong>4 Trajectories</strong> — supported (toy scale)</li> | |
| <li><strong>5 Scores</strong> — unavailable; tables consistent</li> | |
| <li><strong>6 Fig. 3 / Fig. 5</strong> — reproduced / supported</li> | |
| </ul> | |
| <p class="body-text mt-3 fs-3 text-secondary"> | |
| Not device-measured: CUDA peak memory, author Triton kernels, GPT-2 124M arms — the 2-job | |
| GPU protocol is written, frozen by order, not by feasibility. | |
| </p> | |
| <div class="callout gold mt-3"> | |
| <strong>In one sentence:</strong> every mechanism claim we could execute reproduced. | |
| </div> | |
| </div> | |
| </div> | |
| <!-- ============ COLUMN 2 ============ --> | |
| <div class="column" data-measure-role="column"> | |
| <div class="card" data-measure-role="card" data-logbook-target="claim-2-adamw-memory-16-to-7-bytes-per-parameter-5-with-gradient-release" data-logbook-label="Claim 2 evidence"> | |
| <div class="section-title"><span class="num">3</span><span class="st-text">Byte Accounting Is Exact</span></div> | |
| <p class="body-text"> | |
| Table 1 reproduces exactly — <span class="highlight-text">16 → 7.125 → 5.125 B/param</span> with scale overhead — and <strong>19/20</strong> measured rows follow from pure arithmetic. | |
| </p> | |
| <div class="figure mt-3"> | |
| <img src="images/fig_bytes.svg" alt="Stacked bytes-per-parameter accounting for AdamW and SGD variants" class="w-95"> | |
| <div class="caption fs-2">Component stack per variant; GR = gradient release.</div> | |
| </div> | |
| </div> | |
| <div class="card highlight pb-12" data-measure-role="card" data-logbook-target="claim-4-training-loss-trajectories-match-reference-optimizers" data-logbook-label="Claim 4 evidence"> | |
| <div class="section-title"><span class="num">4</span><span class="st-text">Companding Is Necessary <span class="tag-key fs-3">★</span></span></div> | |
| <p class="body-text text-secondary fs-3 mb-1"> | |
| Char-LM (2.4M params, Tiny Shakespeare, 500 steps), four arms, identical data order; toy scale, CPU. | |
| </p> | |
| <div class="figure"> | |
| <img src="images/fig_traj.svg" alt="Training loss trajectories: reference seeds, companded FlashAdamW, and diverging linear-quantization arm" class="w-95"> | |
| <div class="caption fs-2"> | |
| <strong>Red:</strong> linear states → NaN, as Fig. 5 predicts. <strong>Green:</strong> companded tracks | |
| reference <em>inside seed noise</em> — mean |Δloss| 0.0055 vs 0.0084. | |
| </div> | |
| </div> | |
| <p class="body-text mt-3"> | |
| Why: linear uint8 variance has NMSE <span class="keyword">0.746</span>; sqrt companding cuts it | |
| <span class="highlight-text">78,000×</span>, matching Fig. 4. | |
| </p> | |
| <div class="figure mt-2"> | |
| <img src="images/fig_nmse.svg" alt="NMSE distributions: companded vs linear quantization of momentum and variance" class="w-95"> | |
| <div class="caption fs-2">NMSE quantiles over harvested optimizer states.</div> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| <!-- ============================ FOOTER ============================ --> | |
| <div class="footer" data-measure-role="footer"> | |
| <div> | |
| <strong class="method-name">Repro: FlashOptim</strong> · arXiv 2602.23349 · local CPU only, $0.00 paid | |
| </div> | |
| <div> | |
| Code audited: <span class="repo">github.com/databricks/flashoptim</span> · | |
| Bundle: <span class="repo">hf.co/buckets/ProCreations/flashoptim-repro-artifacts</span> | |
| </div> | |
| </div> | |
| <!-- Optional watermark — delete if you don't want it. --> | |
| <div class="ornament">ICML 2026 · AGENT REPRODUCTION CHALLENGE</div> | |
| </div> | |
| </body> | |
| </html> | |
Xet Storage Details
- Size:
- 43.5 kB
- Xet hash:
- 90867ca35a375ed14ac71e6d92c9d888174e4e1a2ab65bd93bdcf15aac6bbe7e
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.