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 99 for “"Vision-Language Models (VLMs)"”.

  1. Vision and language : representation learning, commonsense reasoning, and consistency

    Vision-Language Models (VLMs), a prominent sub-class of multimodal architectures, are important because they allow automated systems to process and understand both visual and linguistic data, enabling more intuitive and accessible interactions. They bridge a gap between language and vision, leading …

    ubc Repository record for Vision and language : representation learning, commonsense reasoning, and consistency (opens in a new tab) Download PDF for Vision and language : representation learning, commonsense reasoning, and consistency (opens in a new tab)

  2. Solving the Bongard Problems with Language and Code

    Vision-Language Models (VLMs) have made great strides in everyday visual tasks, such as captioning a natural image, or answering commonsense questions about such images. But humans possess the puzzling ability to deploy their visualreasoning abilities in radically new situations – a skill …

    cornell Repository record for Solving the Bongard Problems with Language and Code (opens in a new tab) Embargoed until 2027-09-09

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

    Multimodal 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)

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

    … no investigation into whether contemporary Large Language 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 …

    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)

  5. Analysis of algorithms to reduce hallucinations in vision language models /

    Vision-Language Models (VLMs) exhibit impressive multimodal capabilities but remain susceptible to hallucinations — fluent yet visually ungrounded or factually incorrect outputs. This thesis analyzes a white-box hallucination detection framework, Multi-Token Reliability Estimation (MTRE), applied …

    vilnius Repository record for Analysis of algorithms to reduce hallucinations in vision language models / (opens in a new tab)

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

    … a novel task of data 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 …

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

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

    … this limitation, we proposed a novel computer vision framework that leverages visible chimney features as proxies for wood stove usage. Using data from drones, vehicle-based videos across urban and rural areas, we trained object detection models (YOLOv11) and integrated them with Vision …

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

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

    … a lightweight steering module 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 …

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

  9. Efficient model adaptation and compression for edge intelligence

    … success through large-scale pre-training of language and vision models, followed by task-specific adaptation. However, deploying such models on mobile and edge platforms remains challenging due to the limited memory capacity and shared computational resources inherent to these devices. These …

    texas Repository record for Efficient model adaptation and compression for edge intelligence (opens in a new tab)

  10. Stereotyping in Language (Technologies): An Examination of Racial and Gender Stereotypes in Natural Language and Language Models

    … examines stereotyping across natural language and language technologies through three interconnected studies. The first chapter applies a contemporary model of race relations from social psychology to investigate America's racial framework within American English, revealing how …

    wustl Repository record for Stereotyping in Language (Technologies): An Examination of Racial and Gender Stereotypes in Natural Language and Language Models (opens in a new tab)

  11. 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

  12. Shaping Rewards with Temporal Information to Guide Reinforcement Learning

    … learning (RL) methods that apply pretrained Vision-Language Models (VLMs) to compute rewards typically use a single observation of the environment to do so. This is problematic because any information emerging from the sequential nature of RL, i.e. temporal information, is therefore …

    chalmers Repository record for Shaping Rewards with Temporal Information to Guide Reinforcement Learning (opens in a new tab)

  13. COMPOSITIONAL REASONING AND PLANNING WITH FOUNDATION MODELS

    Foundation models are pre-trained by internet-scale data and possess vast knowledge. However, they struggle with compositional tasks in reasoning and planning. In those tasks, evidence is scattered across multiple sources and needs to be considered together simultaneously or connected in a …

    nus Repository record for COMPOSITIONAL REASONING AND PLANNING WITH FOUNDATION MODELS (opens in a new tab) Download file for COMPOSITIONAL REASONING AND PLANNING WITH FOUNDATION MODELS (opens in a new tab)

  14. Improving Semi Supervised Few-Shot Recognition by Post-Hoc Correction

    … domains remains a persistent challenge for vision systems, especially under limited supervision. In this work, we explore a post-hoc correction framework that combines a strong semi-supervised few-shot discriminative model (SWIFT) with a powerful vision-language model (Qwen-2.5 VL) to …

    tamu Repository record for Improving Semi Supervised Few-Shot Recognition by Post-Hoc Correction (opens in a new tab) Embargoed until 2027-12-01

  15. Improving Semi Supervised Few-Shot Recognition by Post-Hoc Correction

    … domains remains a persistent challenge for vision systems, especially under limited supervision. In this work, we explore a post-hoc correction framework that combines a strong semi-supervised few-shot discriminative model (SWIFT) with a powerful vision-language model (Qwen-2.5 VL) to …

    tamu Repository record for Improving Semi Supervised Few-Shot Recognition by Post-Hoc Correction (opens in a new tab) Embargoed until 2027-12-01

  16. Improving Semi Supervised Few-Shot Recognition by Post-Hoc Correction

    … domains remains a persistent challenge for vision systems, especially under limited supervision. In this work, we explore a post-hoc correction framework that combines a strong semi-supervised few-shot discriminative model (SWIFT) with a powerful vision-language model (Qwen-2.5 VL) to …

    tamu Repository record for Improving Semi Supervised Few-Shot Recognition by Post-Hoc Correction (opens in a new tab) Embargoed until 2027-12-01

  17. Improving Semi Supervised Few-Shot Recognition by Post-Hoc Correction

    … domains remains a persistent challenge for vision systems, especially under limited supervision. In this work, we explore a post-hoc correction framework that combines a strong semi-supervised few-shot discriminative model (SWIFT) with a powerful vision-language model (Qwen-2.5 VL) to …

    tamu Repository record for Improving Semi Supervised Few-Shot Recognition by Post-Hoc Correction (opens in a new tab) Embargoed until 2027-12-01

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

    In the past few years, contrastively 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 …

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

  19. Robustness of Vision Language Models for Pedestrian Detection Tasks

    … where failures can carry 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 …

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

  20. LANGUAGE MODELS FOR ROBOT TASK PLANNING WITH HUMAN DEMONSTRATIONS

    … addresses these challenges leveraging Large Language Models (LLMs) and Vision-Language Models (VLMs) to convert task demonstrations to robot code offline, then adapt to changes planning online. This work is divided into three connected components. Firstly, we developed DEMO2CODE, that …

    cornell Repository record for LANGUAGE MODELS FOR ROBOT TASK PLANNING WITH HUMAN DEMONSTRATIONS (opens in a new tab)

Page 1 of 5