FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation

A quarterly journal on warm paper, one vermilion pen, and a margin index that follows you down the page.

focavla.github.ioFOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation
Screenshot of https://focavla.github.io/, © the authors. Shown for reference. Request removal
Venue
ICML 2026
Year
2026
First author
Duc Minh Nguyen
Field
vision-language-action models
Template
Hand-built on Tailwind 3.4.16 Play CDN with OKLCH tokens and Lucide icons
Theme
Light

Checked against the rendered page. body zoom 0.8 at >=1024px shrinks all declared sizes (11px kickers render at 8.8px); file reports rendered desktop size with declared size in parentheses. --primary and --muted tokens are declared but unused. OKLCH tokens converted to hex.

Why it is here

Editorial serif headline with a single vermilion accent, small-caps section kickers, a sticky numbered contents rail and a stat column beside the abstract. Strong hierarchy, comfortable measure, and figures sit in neatly captioned frames.

Overview

Color Palette

Typography

Source Serif 4
FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language- Abstract · Method · Results · BibTeX — 0123456789
Inter
FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language- Abstract · Method · Results · BibTeX — 0123456789
JetBrains Mono
FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language- Abstract · Method · Results · BibTeX — 0123456789

Spacing & Shape

Page Modules

Guidelines

More like this