Cover Image

A Simple yet Effective Layout Token in Large Language Models for Document Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhu, Zhaoqing, Luo, Chuwei, Shao, Zirui, Gao, Feiyu, Xing, Hangdi, Zheng, Qi, Zhang, Ji
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding
by: Luo, Chuwei, et al.
Published: (2024)

Is Cognition Consistent with Perception? Assessing and Mitigating Multimodal Knowledge Conflicts in Document Understanding
by: Shao, Zirui, et al.
Published: (2024)

WebRPG: Automatic Web Rendering Parameters Generation for Visual Presentation
by: Shao, Zirui, et al.
Published: (2024)

DTP: A Simple yet Effective Distracting Token Pruning Framework for Vision-Language Action Models
by: Li, Chenyang, et al.
Published: (2026)

ProcTag: Process Tagging for Assessing the Efficacy of Document Instruction Data
by: Shen, Yufan, et al.
Published: (2024)

Bi-VLDoc: Bidirectional Vision-Language Modeling for Visually-Rich Document Understanding
by: Luo, Chuwei, et al.
Published: (2022)

Doc-CoB: Enhancing Document Understanding with Visual Chain-of-Boxes Reasoning
by: Mo, Ye, et al.
Published: (2025)

LayoutCoT: Unleashing the Deep Reasoning Potential of Large Language Models for Layout Generation
by: Shi, Hengyu, et al.
Published: (2025)

FIND: A Simple yet Effective Baseline for Diffusion-Generated Image Detection
by: Li, Jie, et al.
Published: (2026)

CubeFormer: A Simple yet Effective Baseline for Lightweight Image Super-Resolution
by: Wang, Jikai, et al.
Published: (2024)

FipTR: A Simple yet Effective Transformer Framework for Future Instance Prediction in Autonomous Driving
by: Gui, Xingtai, et al.
Published: (2024)

PPTBench: Towards Holistic Evaluation of Large Language Models for PowerPoint Layout and Design Understanding
by: Huang, Zheng, et al.
Published: (2025)

Aligning Effective Tokens with Video Anomaly in Large Language Models
by: Chen, Yingxian, et al.
Published: (2025)

Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs
by: Song, Dingjie, et al.
Published: (2024)

LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding
by: Fujitake, Masato
Published: (2024)

LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness
by: Zhu, Chenming, et al.
Published: (2024)

LORE++: Logical Location Regression Network for Table Structure Recognition with Pre-training
by: Long, Rujiao, et al.
Published: (2024)

DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding
by: Zhang, Hongzhi, et al.
Published: (2025)

HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Poses
by: Ma, Caoyuan, et al.
Published: (2023)

LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation
by: Zheng, Guangcong, et al.
Published: (2023)

Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation
by: Ding, Shuangrui, et al.
Published: (2023)

Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing
by: Lin, Haonan, et al.
Published: (2024)

LLplace: The 3D Indoor Scene Layout Generation and Editing via Large Language Model
by: Yang, Yixuan, et al.
Published: (2024)

ReLayout: Towards Real-World Document Understanding via Layout-enhanced Pre-training
by: Jiang, Zhouqiang, et al.
Published: (2024)

Temporal Visual Semantics-Induced Human Motion Understanding with Large Language Models
by: Xing, Zheng, et al.
Published: (2025)

DINO-Detect: A Simple yet Effective Framework for Blur-Robust AI-Generated Image Detection
by: Shen, Jialiang, et al.
Published: (2025)

DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs
by: Meng, Lingchen, et al.
Published: (2024)

Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization
by: Kang, Seongjae, et al.
Published: (2025)

A Simple yet Effective Test-Time Adaptation for Zero-Shot Monocular Metric Depth Estimation
by: Marsal, Rémi, et al.
Published: (2024)

Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations
by: Wang, Yuji, et al.
Published: (2025)

A Simple yet Effective Network based on Vision Transformer for Camouflaged Object and Salient Object Detection
by: Hao, Chao, et al.
Published: (2024)

A Simple yet Effective Subway Self-positioning Method based on Aerial-view Sleeper Detection
by: Song, Jiajie, et al.
Published: (2024)

Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models
by: Li, Xin, et al.
Published: (2024)

A Token-level Text Image Foundation Model for Document Understanding
by: Guan, Tongkun, et al.
Published: (2025)

Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding
by: Zhang, Renshan, et al.
Published: (2024)

ReLayout: Integrating Relation Reasoning for Content-aware Layout Generation with Multi-modal Large Language Models
by: Tian, Jiaxu, et al.
Published: (2025)

RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
by: Chen, Yufan, et al.
Published: (2024)

TokenCompose: Text-to-Image Diffusion with Token-level Supervision
by: Wang, Zirui, et al.
Published: (2023)

Relation-Aware Diffusion Model for Controllable Poster Layout Generation
by: Li, Fengheng, et al.
Published: (2023)

EchoGen: Cycle-Consistent Learning for Unified Layout-Image Generation and Understanding
by: Zou, Kai, et al.
Published: (2026)