相关论文: GutenOCR: A Grounded Vision-Language Front-End for…

Recent work has shown that Vision-Language Models (VLMs) used for optical character recognition (OCR) can generate plausible but visually unsupported text, suggesting reliance on language priors. Comparing open-weight VLMs with traditional…

Document Layout Parsing serves as a critical gateway for Artificial Intelligence (AI) to access and interpret the world's vast stores of structured knowledge. This process,which encompasses layout detection, text recognition, and relational…

Models like OpenAI-o3 pioneer visual grounded reasoning by dynamically referencing visual regions, just like human "thinking with images". However, no benchmark exists to evaluate these capabilities holistically. To bridge this gap, we…

Despite significant advances in document understanding, determining the correct orientation of scanned or photographed documents remains a critical pre-processing step in the real world settings. Accurate rotation correction is essential…

We present Multimodal OCR (MOCR), a document parsing paradigm that jointly parses text and graphics into unified textual representations. Unlike conventional OCR systems that focus on text recognition and leave graphical regions as cropped…

Language models have been supervised with both language-only objective and visual grounding in existing studies of visual-grounded language learning. However, due to differences in the distribution and scale of visual-grounded datasets and…

Multimodal Large Language Models (MLLMs) have increasingly localized and interleaved visual evidence for deliberative reasoning. Grounding-based approaches typically focus on regions of interest (RoIs) by injecting cropped image patches or…

In this paper, we present ZonUI-3B, a lightweight Vision-Language Model (VLM) that can be fully trained on a single consumer-grade GPU (RTX 4090) while delivering performance comparable to significantly larger models on GUI grounding tasks.…

In recent years, multimodal large models have continued to improve on general benchmarks. However, in real-world content moderation and adversarial settings, mainstream models still suffer from degraded generalization and catastrophic…

Manchu, a critically endangered language essential for understanding early modern Eastern Eurasian history, lacks effective OCR systems that can handle real-world historical documents. This study develops high-performing OCR systems by…

Document parsing is a fine-grained task where image resolution significantly impacts performance. While advanced research leveraging vision-language models benefits from high-resolution input to boost model performance, this often leads to…

Vision-Language Models (VLMs) have shown strong promise on Optical Character Recognition (OCR), yet the sheer number of visual tokens required to encode dense documents incurs prohibitive inference cost. Existing pruning methods rely on…

Visual grounding aims to identify objects or regions in a scene based on natural language descriptions, essential for spatially aware perception in autonomous driving. However, existing visual grounding tasks typically depend on bounding…

Visual grounding in text-rich document images is a critical yet underexplored challenge for Document Intelligence and Visual Question Answering (VQA) systems. We present DRISHTIKON, a multi-granular and multi-block visual grounding…

We present DeepSeek-OCR as an initial investigation into the feasibility of compressing long contexts via optical 2D mapping. DeepSeek-OCR consists of two components: DeepEncoder and DeepSeek3B-MoE-A570M as the decoder. Specifically,…

We introduce MinerU2.5, a 1.2B-parameter document parsing vision-language model that achieves state-of-the-art recognition accuracy while maintaining exceptional computational efficiency. Our approach employs a coarse-to-fine, two-stage…

Current visual grounding models are either based on a Multimodal Large Language Model (MLLM) that performs auto-regressive decoding, which is slow and risks hallucinations, or on re-aligning an LLM with vision features to learn new special…

We open-source MiMo-VL-7B-SFT and MiMo-VL-7B-RL, two powerful vision-language models delivering state-of-the-art performance in both general visual understanding and multimodal reasoning. MiMo-VL-7B-RL outperforms Qwen2.5-VL-7B on 35 out of…

We introduce Qwen3-VL, the most capable vision-language model in the Qwen series to date, achieving superior performance across a broad range of multimodal benchmarks. It natively supports interleaved contexts of up to 256K tokens,…

Multimodal reasoning has become a cornerstone of modern AI research. Standardized exam questions offer a uniquely rigorous testbed for such reasoning, providing structured visual contexts and verifiable answers. While recent progress has…