Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoning
A cream editorial broadsheet with a drafting-grid hero, pill controls and figures mounted on white plates.
Checked against the rendered page. Lower sections were caught mid scroll-reveal (faded) in the full-page capture; their values come from CSS and computed styles.
Why it is here
Polished centred serif hero with a pill venue badge, affiliation logos and a refined button row, plus a large teaser card with a caption. The TL;DR and abstract split and the big stat numerals are elegant. Lower sections were caught mid scroll-reveal (faded), which is a minor capture issue.
Overview
Color Palette
Typography
Newsreader
Unleashing Spatial Reasoning in Multimodal Large Language Models via T
Abstract · Method · Results · BibTeX — 0123456789
Inter
Unleashing Spatial Reasoning in Multimodal Large Language Models via T
Abstract · Method · Results · BibTeX — 0123456789
JetBrains Mono
Unleashing Spatial Reasoning in Multimodal Large Language Models via T
Abstract · Method · Results · BibTeX — 0123456789
Spacing & Shape
Page Modules
Guidelines
More like this
CRAFT: Training-Free Cascaded Retrieval for Tabular QA
A tidy product manual in pale blueprint blue, where every stage wears its own colored edge.
Efficient Self-Evaluation for Diffusion Language Models via Sequence Regeneration
A tidy stack of rounded cards washed in a blue-violet-apricot dawn, signed with a gradient wordmark.
FIGMA: Towards FIne-Grained Music retrievAl
A music journal on warm paper: a heavy Newsreader headline under a red kicker, big red serif numerals for the results, and figures resting in soft cream frames.
GuideDog: A Real-World Egocentric Multimodal Dataset for Blind and Low-Vision Accessibility-Aware Guidance
A quiet monograph page: one serif column, oxblood ink for the links, and a table that blushes only at its own row.
LaMI: Augmenting Large Language Models via Late Multi-Image Fusion
A careful conference handout: Noto Serif headings, navy outlined buttons and soft grey bands taking turns.
PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation
A crisp white product page: a blue announcement strip, ink-black pill buttons and every figure on a soft-shadowed card.