FocalOrder: Focal Preference Optimization for Reading Order Detection
Fuyuan Liu, Dianyu Yu, He Ren, Nayu Liu, Xiaomian Kang, Delai Qiu, Fa Zhang, Genpeng Zhen, Shengping Liu, Jiaen Liang, Wei Huang, Yining Wang, Junnan Zhu

TL;DR
FocalOrder introduces a novel training framework that dynamically identifies and emphasizes difficult reading order transitions in documents, significantly improving understanding accuracy over existing methods.
Contribution
The paper proposes FocalOrder with Focal Preference Optimization, addressing positional disparity by focusing on hard-to-learn layout transitions, advancing document reading order detection.
Findings
Achieves state-of-the-art results on OmniDocBench v1.0 and Comp-HRDoc.
Outperforms both specialized baselines and large-scale general VLMs.
Demonstrates the importance of difficulty-aware optimization for complex document structures.
Abstract
Reading order detection is the foundation of document understanding. Most existing methods rely on uniform supervision, implicitly assuming a constant difficulty distribution across layout regions. In this work, we challenge this assumption by revealing a critical flaw: \textbf{Positional Disparity}, a phenomenon where models demonstrate mastery over the deterministic start and end regions but suffer a performance collapse in the complex intermediate sections. This degradation arises because standard training allows the massive volume of easy patterns to drown out the learning signals from difficult layouts. To address this, we propose \textbf{FocalOrder}, a framework driven by \textbf{Focal Preference Optimization (FPO)}. Specifically, FocalOrder employs adaptive difficulty discovery with exponential moving average mechanism to dynamically pinpoint hard-to-learn transitions, while…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHandwritten Text Recognition Techniques · Text Readability and Simplification · Topic Modeling
