AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

LaTeX2Layout: High-Fidelity, Scalable Document Layout Annotation Pipeline for Layout Detection

Feijiang Han, Zelong Wang, Bowen Wang, Xinxin Liu, Skyler Cheung, Delip Rao, Chris Callison-Burch, Lyle Ungar

AAAI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Fine-tune Qwen2.5-VL-3B on LaTeX2Layout data vs zero-shot GPT-4oQwen2.5-VL-3B · Layout test setmAP50 / Kendall tau: tau 0.31 -> 0.95; mAP50 0.34 -> 0.91Improved
Add 120K synthetic pages to 20K real pages (ablation)Fine-tuned Qwen2.5-VL-3B · Layout test setelement grounding mAP50: 0.78 -> 0.91Improved
Add 120K synthetic pages to 20K real pages (ablation)Fine-tuned Qwen2.5-VL-3B · Layout test setreading order tau: 0.91 -> 0.95Improved
Add 120K synthetic pages (ablation)Fine-tuned Qwen2.5-VL-3B · footnote classmAP50: 0.57 -> 0.87Improved
Add 120K synthetic pages (ablation)Fine-tuned Qwen2.5-VL-3B · math classmAP50: 0.55 -> 0.90Improved
Train on 20K synthetic instead of 20K real (ablation)Qwen2.5-VL-3B · Layout test setreading order tau: 0.91 -> 0.90No clear effect
Scale synthetic data from 20K upward (ablation)Qwen2.5-VL-3B · Layout test setgrounding mAP50Improved
Scale synthetic data from 20K upward (ablation)Qwen2.5-VL-3B · Layout test setreading order tauNo clear effect
Add easy-to-hard curriculum re-ranking (ablation)Qwen2.5-VL-3B (20K real) · Layout test setreading order tau: 0.88 -> 0.91Improved
Add easy-to-hard curriculum re-ranking (ablation)Qwen2.5-VL-3B (20K real) · Layout test setaverage mAP50: 0.72 -> 0.78Improved
Add easy-to-hard curriculum re-ranking (ablation)Qwen2.5-VL-3B (20K real) · footnote classmAP50: 0.28 -> 0.57Improved
Add curriculum re-ranking (ablation)Qwen2.5-VL-3B (20K real) · Layout test set, per-classmAP50: Tit 0.77 -> 0.75; TabCap 0.81 -> 0.78; Head 0.66 -> 0.73Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy