Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos
A Nerfies page that learned to curate: a tight masthead, a gallery that peeks past the margins, and a pale-blue reading room.
Checked against the rendered page. The TL;DR and narrative-column fills were sampled from the screenshots.
Why it is here
Most complete composition: tight centered header with pill buttons and tinted TL;DR, a full-bleed 3D carousel gallery that peeks at neighbouring slides, then a tinted narrative column interleaving figures and prose. Confident hierarchy, nothing broken.
Overview
Color Palette
Typography
Google Sans
Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos
Abstract · Method · Results · BibTeX — 0123456789
Segoe UI / system UI
Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos
Abstract · Method · Results · BibTeX — 0123456789
Noto Sans
Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos
Abstract · Method · Results · BibTeX — 0123456789
Spacing & Shape
Page Modules
Guidelines
More like this
Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation
A university press catalogue: small-caps serif title, a colour wheel of specimens and an earthy bar chart.
DICE-BENCH: Evaluating the Tool-Use Capabilities of Large Language Models in Multi-Round, Multi-Party Dialogues
A Nerfies page with a game-box cover: a charcoal dice banner stamps the identity, then pastel brand-tinted pills and a grey carousel strip carry you into a quiet two-column method read.
TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos
A benchmark that leads with its scoreboard: a fish-logo small-caps wordmark, a gradient venue line, then a full-width grey-headed leaderboard with zebra rows and blue model links.
Gesturing Toward Abstraction: Multimodal Convention Formation in Collaborative Physical Tasks
A seminar handout on clean paper: a big soft headline, six charcoal tabs, and a teal-and-magenta comic strip of hands explaining blocks.
Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework
A lab notebook opened to its best page: a framed video like a monitor bezel, emoji in the headline, and every figure pinned with a soft shadow.
What If Moderation Didn't Mean Suppression? A Case for Personalized Content Transformation
A quiet reading room with a purple ribbon on the lectern: slate sans headlines, Garamond prose, and one warm amber note pinned to the wall.