Related papers: FireRed-OCR Technical Report

This paper presents HunyuanOCR, a commercial-grade, open-source, and lightweight (1B parameters) Vision-Language Model (VLM) dedicated to OCR tasks. The architecture comprises a Native Vision Transformer (ViT) and a lightweight LLM…

We present DeepSeek-OCR 2 to investigate the feasibility of a novel encoder-DeepEncoder V2-capable of dynamically reordering visual tokens upon image semantics. Conventional vision-language models (VLMs) invariably process visual tokens in…

Document parsing (DP) transforms unstructured or semi-structured documents into structured, machine-readable representations, enabling downstream applications such as knowledge base construction and retrieval-augmented generation (RAG).…

Real-world License Plate Recognition (LPR) faces significant challenges from severe degradations such as motion blur, low resolution, and complex illumination. The prevailing "restoration-then-recognition" two-stage paradigm suffers from a…

This technical report introduces PaddleOCR 3.0, an Apache-licensed open-source toolkit for OCR and document parsing. To address the growing demand for document understanding in the era of large language models, PaddleOCR 3.0 presents three…

Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large language model (LLM). This unified input paradigm enables VLMs to…

In recent years, Multi-modal Large Language Models (MLLMs) have achieved strong performance in OCR-centric Visual Question Answering (VQA) tasks, illustrating their capability to process heterogeneous data and exhibit adaptability across…

Structure information is critical for understanding the semantics of text-rich images, such as documents, tables, and charts. Existing Multimodal Large Language Models (MLLMs) for Visual Document Understanding are equipped with text…

We present a novel OCR-free document understanding framework based on pretrained Multimodal Large Language Models (MLLMs). Our approach employs multi-scale visual features to effectively handle various font sizes within document images. To…

Optical Character Recognition (OCR) is increasingly regarded as a foundational capability for modern vision-language models (VLMs), enabling them not only to read text in images but also to support downstream reasoning in real-world visual…

Document parsing has recently advanced with multimodal large language models (MLLMs) that directly map document images to structured outputs. Traditional cascaded pipelines depend on precise layout analysis and often fail under casually…

Currently, instruction-based image editing methods have made significant progress by leveraging the powerful cross-modal understanding capabilities of vision language models (VLMs). However, they still face challenges in three key areas: 1)…

While Vision-Language Models (VLMs) achieve near-perfect scores on digital document benchmarks like OmniDocBench, their performance in the unpredictable physical world remains largely unknown due to the lack of controlled yet realistic…

Converting raster floorplans into engineering-grade vector graphics is challenging due to complex topology and strict geometric constraints. To address this, we present FloorplanVLM, a unified framework that reformulates floorplan…

The ability of Large Language Models (LLMs) to generate structured outputs that follow arbitrary schemas is crucial to a wide range of downstream tasks that require diverse structured representations of results such as information…

The inherent complexities of Arabic script; its cursive nature, diacritical marks (tashkeel), and varied typography, pose persistent challenges for Optical Character Recognition (OCR). We present Qari-OCR, a series of vision-language models…

While Vision-Language Models (VLMs) enable high-level semantic reasoning for end-to-end autonomous driving, particularly in unstructured environments, existing off-road datasets suffer from language annotations that are weakly aligned with…

With the rise of multimodal large language models, accurately extracting and understanding textual information from video content, referred to as video based optical character recognition (Video OCR), has become a crucial capability. This…

Vision-Language (VL) models have garnered considerable research interest; however, they still face challenges in effectively handling text within images. To address this limitation, researchers have developed two approaches. The first…

Existing Multimodal Large Language Models (MLLMs) for image forgery detection and localization predominantly operate under a text-centric Chain-of-Thought (CoT) paradigm. However, forcing these models to textually characterize imperceptible…