Related papers: GutenOCR: A Grounded Vision-Language Front-End for…

Visual grounding focuses on establishing fine-grained alignment between vision and natural language, which has essential applications in multimodal reasoning systems. Existing methods use pre-trained query-agnostic visual backbones to…

Despite rapid progress, multimodal reasoning still lacks a systematic approach to synthesize large-scale vision-centric datasets beyond visual math. We introduce a framework able to synthesize vision-centric problems spanning diverse levels…

The problem of language grounding has attracted much attention in recent years due to its pivotal role in more general image-lingual high level reasoning tasks (e.g., image captioning, VQA). Despite the tremendous progress in visual…

Text and formulas constitute the core informational components of many documents. Accurately and efficiently recognizing both is crucial for developing robust and generalizable document parsing systems. Recently, vision-language models…

In this report, we propose PaddleOCR-VL, a SOTA and resource-efficient model tailored for document parsing. Its core component is PaddleOCR-VL-0.9B, a compact yet powerful vision-language model (VLM) that integrates a NaViT-style dynamic…

Deploying vision-language models (VLMs) in clinical settings demands auditable behavior under realistic failure conditions, yet the failure landscape of frontier VLMs on specialized medical inputs is poorly characterized. We audit five…

GUI grounding aims to align natural language instructions with precise regions in complex user interfaces. Advanced multimodal large language models show strong ability in visual GUI grounding but still struggle with small or visually…

We present STEP3-VL-10B, a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence. STEP3-VL-10B is realized through two strategic shifts: first, a…

Recent Vision-Language-Action (VLA) models have made impressive progress toward general-purpose robotic manipulation by post-training large Vision-Language Models (VLMs) for action prediction. Yet most VLAs entangle perception and control…

Reading dense text and locating objects within images are fundamental abilities for Large Vision-Language Models (LVLMs) tasked with advanced jobs. Previous LVLMs, including superior proprietary models like GPT-4o, have struggled to excel…

Recent advances in vision-language models (VLMs) have enabled end-to-end document parsing and understanding, achieving strong performance on diverse optical character recognition (OCR) tasks. However, VLMs are prone to generate words that…

Arabic document OCR remains a challenging task due to the language's cursive script, diverse fonts, diacritics, and right-to-left orientation. While modern Multimodal Large Language Models (MLLMs) have advanced document understanding for…

Long-document topic segmentation plays an important role in information retrieval and document understanding, yet existing methods still show clear shortcomings in ultra-long text settings. Traditional discriminative models are constrained…

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…

GLM-OCR is an efficient 0.9B-parameter compact multimodal model designed for real-world document understanding. It combines a 0.4B-parameter CogViT visual encoder with a 0.5B-parameter GLM language decoder, achieving a strong balance…

Vision-language models can connect the text description of an object to its specific location in an image through visual grounding. This has potential applications in enhanced radiology reporting. However, these models require large…

In this work, we introduce the Qwen-VL series, a set of large-scale vision-language models (LVLMs) designed to perceive and understand both texts and images. Starting from the Qwen-LM as a foundation, we endow it with visual capacity by the…

Modern vision-language models (VLMs) can act as generative OCR engines, yet open-ended decoding can expose rare but consequential failures. We identify a core deployment misalignment in generative OCR. Autoregressive decoding favors…

Existing forgery detection methods are often limited to uni-modal or bi-modal settings, failing to handle the interleaved text, images, and videos prevalent in real-world misinformation. To bridge this gap, this paper targets to develop a…

Unsupervised pre-training on millions of digital-born or scanned documents has shown promising advances in visual document understanding~(VDU). While various vision-language pre-training objectives are studied in existing solutions, the…