activity
20242026
collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2026

P-MTP: Efficient Document Parsing via Multi-Token Prediction with Progressive Depth Scaling

Le Xiang, Chenxi Zhai, Shu Wei +5

Vision-Language Models (VLMs) have revolutionized document parsing by enabling end-to-end mapping from images to structured text, imposing a significant latency bottleneck, particu…

cs.CV2026

Unlimited OCR Works

Youyang Yin, Huanhuan Liu, YY +14

Recently, end-to-end OCR models, exemplified by DeepSeek OCR, have once again thrust OCR into the spotlight. A widely held view is that employing a large language model (LLM) as th…

cs.CV2025

Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting

Hao Feng, Shu Wei, Xiang Fei +10

Document image parsing is challenging due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables. Current approaches either assemble specializ…

cs.CV2024

Harmonizing Visual Text Comprehension and Generation

Zhen Zhao, Jingqun Tang, Binghong Wu +7

In this work, we present TextHarmony, a unified and versatile multimodal generative model proficient in comprehending and generating visual text. Simultaneously generating images a…

cs.CV2024

TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy

Weichao Zhao, Hao Feng, Qi Liu +9

Tables contain factual and quantitative data accompanied by various structures and contents that pose challenges for machine comprehension. Previous methods generally design task-s…

cs.CV2024

MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering

Jingqun Tang, Qi Liu, Yongjie Ye +14

Text-Centric Visual Question Answering (TEC-VQA) in its proper format not only facilitates human-machine interaction in text-centric visual environments but also serves as a de fac…