Related papers: Exploring the Capabilities of Vision-Language Mode…
Vision-language models (VLMs) have recently emerged as powerful representation learning systems that align visual observations with natural language concepts, offering new opportunities for semantic reasoning in safety-critical autonomous…
The combination of computer vision and artificial intelligence is fundamentally transforming a broad spectrum of industries by enabling machines to interpret and act upon visual data with high levels of accuracy. As the biggest and by far…
Most production-level deployments for Visual Question Answering (VQA) tasks are still build as processing pipelines of independent steps including image pre-processing, object- and text detection, Optical Character Recognition (OCR) and…
We present DeepSeek-VL, an open-source Vision-Language (VL) Model designed for real-world vision and language understanding applications. Our approach is structured around three key dimensions: We strive to ensure our data is diverse,…
Numerous approaches employing various strategies have been developed to test the graphical user interfaces (GUIs) of mobile apps. However, traditional GUI testing techniques, such as random and model-based testing, primarily focus on…
The increasing integration of Visual Language Models (VLMs) into visualization systems demands a comprehensive understanding of their visual interpretation capabilities and constraints. While existing research has examined individual…
This paper presents novel benchmarks for evaluating vision-language models (VLMs) in zero-shot recognition, focusing on granularity and specificity. Although VLMs excel in tasks like image captioning, they face challenges in open-world…
The widespread use of cameras in our society has created an overwhelming amount of video data, far exceeding the capacity for human monitoring. This presents a critical challenge for public safety and security, as the timely detection of…
The increasing integration of Visual Language Models (VLMs) into AI systems necessitates robust model alignment, especially when handling multimodal content that combines text and images. Existing evaluation datasets heavily lean towards…
Large language models (LLMs) are increasingly used to generate requirements specifications, design documents, code, and test cases. In contrast, much less attention has been given to a more difficult assurance problem: statically verifying…
Recent large-scale vision-language models (VLMs) have demonstrated remarkable capabilities in understanding and generating textual descriptions for visual content. However, these models lack an understanding of user-specific concepts. In…
Recent advances in Vision-Language Models (VLMs) have achieved impressive progress in multimodal mathematical reasoning. Yet, how much visual information truly contributes to reasoning remains unclear. Existing benchmarks report strong…
WebAssembly (abbreviated WASM) has emerged as a promising language of the Web and also been used for a wide spectrum of software applications such as mobile applications and desktop applications. These applications, named as WASM…
Multi-modal Large Langue Models (MLLMs) often process thousands of visual tokens, which consume a significant portion of the context window and impose a substantial computational burden. Prior work has empirically explored visual token…
Visual text evokes an image in a person's mind, while non-visual text fails to do so. A method to automatically detect visualness in text will enable text-to-image retrieval and generation models to augment text with relevant images. This…
Image-to-code generation tests whether a vision-language model (VLM) can recover the structure of an image enough to express it as executable code. Existing benchmarks either focus on narrow visual domains, depend on paired executable…
Vision-language models (VLMs) excel in visual understanding but often lack reliable grounding capabilities and actionable inference rates. Integrating them with open-vocabulary object detection (OVD), instance segmentation, and tracking…
Since the release of ChatGPT, the field of Natural Language Processing has experienced rapid advancements, particularly in Large Language Models (LLMs) and their multimodal counterparts, Large Multimodal Models (LMMs). Despite their…
Vision-Language Pre-training (VLP) has advanced the performance of many vision-language tasks, such as image-text retrieval, visual entailment, and visual reasoning. The pre-training mostly utilizes lexical databases and image queries in…
Detecting vulnerabilities in source code remains critical yet challenging, as conventional static analysis tools construct inaccurate program representations, while existing LLM-based approaches often miss essential vulnerability context…