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)"”.
-
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 …
-
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 …
-
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, …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
Page 1 of 5