Related papers: DeepSeek-OCR 2: Visual Causal Flow

Vision-Language Models often struggle with complex visual reasoning due to the visual information loss in textual CoT. Existing methods either add the cost of tool calls or rely on localized patch-based embeddings that are insufficient to…

Complex Visual Question Answering (Complex VQA) tasks, which demand sophisticated multi-modal reasoning and external knowledge integration, present significant challenges for existing large vision-language models (LVLMs) often limited by…

Recent studies on machine reading comprehension have focused on text-level understanding but have not yet reached the level of human understanding of the visual layout and content of real-world documents. In this study, we introduce a new…

Current vision systems typically assign fixed-length representations to images, regardless of the information content. This contrasts with human intelligence - and even large language models - which allocate varying representational…

Vision-Language Models (VLMs) have demonstrated strong capability in a wide range of tasks such as visual recognition, document parsing, and visual grounding. Nevertheless, recent work shows that while VLMs often manage to capture the…

Humans can robustly localize visual evidence and provide grounded answers even in noisy environments by identifying critical cues and then relating them to the full context in a bottom-up manner. Inspired by this, we propose DeepScan, a…

We introduce Visual Caption Restoration (VCR), a novel vision-language task that challenges models to accurately restore partially obscured texts using pixel-level hints within images. This task stems from the observation that text embedded…

Recent advancements in Vision-Language (VL) research have sparked new benchmarks for complex visual reasoning, challenging models' advanced reasoning ability. Traditional Vision-Language Models (VLMs) perform well in visual perception tasks…

Explainability is a longstanding challenge in deep learning, especially in high-stakes domains like healthcare. Common explainability methods highlight image regions that drive an AI model's decision. Humans, however, heavily rely on…

Multi-modal large language models (MLLMs) have achieved remarkable capabilities by integrating visual perception with language understanding, enabling applications such as image-grounded dialogue, visual question answering, and scientific…

The increasing demand for intelligent systems capable of interpreting and reasoning about visual content requires the development of large Vision-and-Language Models (VLMs) that are not only accurate but also have explicit reasoning…

Most existing methods in vision-language retrieval match two modalities by either comparing their global feature vectors which misses sufficient information and lacks interpretability, detecting objects in images or videos and aligning the…

Multimodal large language models (MLLMs) project visual tokens into the embedding space of language models, yet the internal structuring and processing of visual semantics remain poorly understood. In this work, we introduce a two-fold…

We propose an end-to-end recurrent encoder-decoder based sequence learning approach for printed text Optical Character Recognition (OCR). In contrast to present day existing state-of-art OCR solution which uses connectionist temporal…

We present the Qwen2-VL Series, an advanced upgrade of the previous Qwen-VL models that redefines the conventional predetermined-resolution approach in visual processing. Qwen2-VL introduces the Naive Dynamic Resolution mechanism, which…

The advancement of Large Vision-Language Models (LVLMs) requires precise local region-based reasoning that faithfully grounds the model's logic in actual visual evidence. However, existing datasets face limitations in scalability due to…

Despite recent advancements in Multi-modal Large Language Models (MLLMs) on diverse understanding tasks, these models struggle to solve problems which require extensive multi-step reasoning. This is primarily due to the progressive dilution…

Vision-Language Models (VLMs) have shown promising capabilities in handling various multimodal tasks, yet they struggle in long-context scenarios, particularly in tasks involving videos, high-resolution images, or lengthy image-text…

Document parsing has garnered widespread attention as vision-language models (VLMs) advance OCR capabilities. However, the field remains fragmented across dozens of specialized models with varying strengths, forcing users to navigate…

Optical Character Recognition (OCR) is a fundamental task for digitizing information, serving as a critical bridge between visual data and textual understanding. While modern Vision-Language Models (VLM) have achieved high accuracy in this…