Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 124 for “"VLMs"”.

  1. Zero-shot human attribute classification using pretrained VLMs

    Gender and ethnicity recognition is a key computer vision task in biometrics, surveil- lance, and demographic studies. Contrastive Language-Image Pre-training (CLIP) is a Vision-Language Model with promising zero-shot performance in several downstream tasks, without the need for fine-tuning or …

    brazil-ufrgs Repository record for Zero-shot human attribute classification using pretrained VLMs (opens in a new tab)

  2. Zero-Shot Scene Graph Relationship Prediction using VLMs

    … dataset, even when using Vision-Language Models (VLMs). In this work, we propose a training-free framework for the VLMs to predict scene graph relationships. Our approach simply plugs VLMs into the pipeline without any fine-tuning, focusing on how to formulate relationship queries and aggregate …

    vt Repository record for Zero-Shot Scene Graph Relationship Prediction using VLMs (opens in a new tab)

  3. Empirical Study on Adversarial Attacks and Defenses in Vision-Language Models

    Vision-Language Models (VLMs) are widely used for tasks that combine text and images. However, their security risks, especially against adversarial attacks, are not well understood. Although several jailbreak strategies exist for Large Language Models (LLMs), it is unknown whether they also apply …

    tamu Repository record for Empirical Study on Adversarial Attacks and Defenses in Vision-Language Models (opens in a new tab) Embargoed until 2027-05-01

  4. Vision-Language Models: The Overlooked Role of Synonyms

    … pre-trained Vision-Language Models (VLMs) such as CLIP, have significantly propelled advancements in multimodal applications. Pre-trained on internet scale images and captions VLMs learn to associate relevant text and images, making them key to downstream applications such as visual …

    tamu Repository record for Vision-Language Models: The Overlooked Role of Synonyms (opens in a new tab)

  5. Advancing vision-language models for open-vocabulary recognition and generative evaluation

    … and express ourselves. Vision-language models (VLMs) provide promising evidence that AI is progressing toward achieving these capabilities. With VLMs, we can recognize objects using text descriptions, answer questions about images, and generate images from text prompts. Despite this progress, …

    freiburg-diss Repository record for Advancing vision-language models for open-vocabulary recognition and generative evaluation (opens in a new tab)

  6. Robustness of Vision Language Models for Pedestrian Detection Tasks

    … lethal consequences. Vision Language Models (VLMs) have emerged as a promising alternative because they support end-to-end implementations that bypass compounding error risks and provide natural language explanations of their outputs. Despite these advantages, prior research has demonstrated …

    clemson Repository record for Robustness of Vision Language Models for Pedestrian Detection Tasks (opens in a new tab)

  7. Construction safety inspection with large pre-trained vision-language models

    … large pre-trained Vision Language Models (VLMs), researchers are exploring their use for tasks such as detecting safety rule violations from on-site images. However, the question “whether these large models trained on data scraped from the internet understand concepts related to …

    ubc Repository record for Construction safety inspection with large pre-trained vision-language models (opens in a new tab) Download PDF for Construction safety inspection with large pre-trained vision-language models (opens in a new tab)

  8. Beyond Single Images: A Comprehensive Benchmark for Album-Level Vision-Language Understanding

    … photography. Recent Vision-Language Models (VLMs) have shown strong performance on multi-image understanding, making them natural candidates for automating album organization workflows. While VLMs’ abilities in multi-image understanding have been widely studied, their performance on album …

    byu Repository record for Beyond Single Images: A Comprehensive Benchmark for Album-Level Vision-Language Understanding (opens in a new tab) Download PDF for Beyond Single Images: A Comprehensive Benchmark for Album-Level Vision-Language Understanding (opens in a new tab)

  9. Zooming into Comics: Region-Aware RL Improves Fine-Grained Comic Understanding in Vision-Language Models

    … challenge to Vision- Language Models (VLMs). Despite excelling on natural images, VLMs often struggle with stylized line art, onomatopoeia, and densely packed multi-panel layouts. To address this gap, we introduce AI4VA-FG, the first fine-grained and comprehensive benchmark for …

    chalmers Repository record for Zooming into Comics: Region-Aware RL Improves Fine-Grained Comic Understanding in Vision-Language Models (opens in a new tab)

  10. Towards Agentic Vision Language Models for Question Answering on Interactive Dashboard

    … models, specifically Vision Language Models (VLMs), have shown increasing capabilities in data visualization oriented downstream tasks, achieving performance saturation in shorter intervals of time. Consequently, focus has shifted to assessing their potential towards new frontiers, …

    york Repository record for Towards Agentic Vision Language Models for Question Answering on Interactive Dashboard (opens in a new tab)

  11. Synthetic Dataset for Understanding Negation in Text-Guided Image Editing

    … of research means that vision-language models (VLMs) for image editing may struggle to understand negation, implying that they struggle to provide accurate results. One barrier to achieving human-level intelligence is the lack of a standard collection by which research into negation can be …

    arkansas Repository record for Synthetic Dataset for Understanding Negation in Text-Guided Image Editing (opens in a new tab)

  12. Towards Robust and Coherent Data Visualization Generation with Vision–Language Models

    … video generation for Vision Language Models (VLMs), along with a benchmark containing 328 real world data videos. We propose a multi-agent framework for generating better data videos, composed of planning and critic agents, designed to mimic the real-world process of data video generation. …

    york Repository record for Towards Robust and Coherent Data Visualization Generation with Vision–Language Models (opens in a new tab)

  13. Generalizable Adaptation for Vision-Language Models

    Vision-Language Models (VLMs) and Multimodal Large Language Models (MLLMs) have recently emerged as powerful frameworks for learning joint representations across visual and textual modalities. These models enable a wide range of applications, including visual recognition, multimodal reasoning, and …

    clemson Repository record for Generalizable Adaptation for Vision-Language Models (opens in a new tab)

  14. Investigating Zero-Shot Diagnostic Pathology in Vision-Language Models with Efficient Prompt Design

    Vision-Language Models (VLMs) have emerged as powerful tools in computational pathology, offering the ability to perform zero-shot diagnostic inference on gigapixel whole slide images (WSIs). However, a core challenge remains: these models exhibit high sensitivity to the linguistic structure and …

    concordia Download PDF for Investigating Zero-Shot Diagnostic Pathology in Vision-Language Models with Efficient Prompt Design (opens in a new tab)

  15. Mutual exclusivity bias and spatial reasoning in Vision-Language Models

    … rapid progress in large vision-language models (VLMs), we introduce SplatTalk, a novel approach that utilizes multi-view RGB images to address the 3D Visual Question Answering (3D VQA) task, where 3D spatial understanding is essential for achieving high performance. To further investigate the …

    gatech Repository record for Mutual exclusivity bias and spatial reasoning in Vision-Language Models (opens in a new tab)

  16. The Impact of Visual Information in Chinese Characters: Evaluating Large Models’ Ability to Recognize and Utilize Radicals

    … Models (LLMs) and Vision-Language Models (VLMs) can harness these sub-character features in Chinese through prompting. In this study, we establish a benchmark to evaluate LLMs' and VLMs' understanding of visual elements in Chinese characters, including radicals, composition structures, …

    gatech Repository record for The Impact of Visual Information in Chinese Characters: Evaluating Large Models’ Ability to Recognize and Utilize Radicals (opens in a new tab)

  17. AI-Based Framework for Identifying Wood Burning Appliances through Chimney Recognition

    … and integrated them with Vision Language Models (VLMs) for semantic verification. This two-stage pipeline substantially improves detection accuracy over YOLO alone. In the urban Fall Creek neighborhood, the YOLO+VLMs approach achieved an F1-score of 61.4%, compared to 29.3% using YOLO alone. In …

    cornell Repository record for AI-Based Framework for Identifying Wood Burning Appliances through Chimney Recognition (opens in a new tab)

  18. Model Control through Lightweight Activation Steering for Vision Language Models

    … designed to guide Vision- Language Models (VLMs) towards outputs that better adhere to desired instructions. Our approach learns from the latent embeddings of paired prompts encoding target and converse behaviors to dynamically adjust activations connecting the language modality with image …

    vt Repository record for Model Control through Lightweight Activation Steering for Vision Language Models (opens in a new tab)

  19. Towards safer vision-language models : modality-aware vulnerability analysis and adversarial risk assessment.

    Vision-Language Models (VLMs) have become a key technology in modern artificial intelligence, supporting applications such as medical diagnosis, autonomous systems, and content moderation. As these models are increasingly deployed in safety-critical environments, understanding their robustness to …

    baylor Repository record for Towards safer vision-language models : modality-aware vulnerability analysis and adversarial risk assessment. (opens in a new tab)

  20. Integrating Vision-Language Models with Reinforcement Learning for Human-Aligned Decision-Making of Autonomous Vehicles

    … this work utilizes Vision-Language Models (VLMs), particularly CLIP (Contrastive Language-Image Pretraining), to build an additional reward model based on visual and textual cues. CLIP’s ability to align image and text embeddings provides unique features for translating humanlike …

    concordia Download PDF for Integrating Vision-Language Models with Reinforcement Learning for Human-Aligned Decision-Making of Autonomous Vehicles (opens in a new tab)

Page 1 of 7