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 37 for “"Text-to-Image Generation"”.
-
Glass onion: Compositional text-to-image generation using diffusion models and LLMs
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-02-04 without embargo terms
-
Social stereotypes in text-to-image generation: Examining user perceptions and debiasing strategies
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01
-
Applications of Predictive and Generative AI Algorithms: Regression Modeling, Customized Large Language Models, and Text-to-Image Generative Diffusion Models
… Predictive modeling leverages ML and AI to forecast future trends or behaviors based on historical data, while classification tasks categorize data into distinct classes, from email filtering to medical diagnosis. Concurrently, text-to-image generation has emerged as a transformative …
-
Towards Effective Yet Affordable Generative Models for Image Data
… Generative Adversarial Networks, Variational Auto-encoders, Diffusion Models has become one of the most popular research topics in the field of machine learning recently. These models have exhibited an impressive capability to generate realistic image samples, which enables various real-world …
-
Text to Image Synthesis from Scene Descriptions with a Focus on Relative Positioning
Text-to-Image Synthesis (also known as text to image generation) refers to the process of generating images given some input description or caption. While traditional scene generation tools used databases of objects and programmed rules for placement, modern deep-learning systems can infer details …
-
Designing, learning, and utilizing dense reward for generative AI alignment
In this thesis, we aim to mitigate the gap between concrete task domain and reward signal for policy training, with a particular focus on how to design, learn, and utilize dense reward for reinforcement-learning-from-human-feedback (RLHF) training of text and text-to-image generation models. We …
-
Concepts from unclear textual embeddings for text-to-image synthesis
Automatically generating images based on a natural language description is a challenging problem with several key applications in the fields of retail, marketing, education and entertainment. In the last few years, some progress has been made in this direction specifically by using Generative …
-
A Happy Medium?: Using Image Generators to Explore Solution-Focused Art Therapy’s Miracle Question
… single-session study tested whether integrating text-to-image generations into Solution-Focused Brief Art Therapy alters therapeutic rapport and short-term outcomes relative to traditional artmaking materials. Participants were assigned by coin flip to create using either a text-to-image …
-
Vision-Language Models: The Overlooked Role of Synonyms
… 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 chatbots and text-to-image generation diffusion models. However, there has been limited analysis of these models’ …
-
Leveraging the Latent Space for Model Understanding and Optimization
… performance on tasks such as classification or image generation. However, these models are typically limited by two key factors. First, models such as those used in tasks of text-to-image generation lack interpretation. Second, models that leverage the latent space to represent data struggle to …
-
Bridging computer-assisted language learning and cultural approaches: AI-powered game and VR solutions for less commonly taught languages
… interplay of cognitive, social and cultural factors. This complexity is particularly pronounced in the context of Less Commonly Taught Languages (LCTLs), where traditional pedagogical approaches often fall short. This thesis explores the integration of culturally informed approaches with …
-
Advancing Deep Learning through Probability Engineering: A Pragmatic Paradigm for Modern AI
… progression of deep learning, pushing us closer to the realization of AGI (Artificial General Intelligence). Probabilistic modeling is critical to many of these advancements, which provides a foundational framework for capturing data distributions. However, as the scale and complexity of AI …
-
Discovering and Personalizing Artistic Styles with Generative Models
Text-to-image models have gained widespread popularity, transforming digital art creation by allowing users to generate highly detailed and imaginative visual content from natural language prompts. These models are now widely adopted across various domains, particularly in the arts, where they …
-
Efficient and Scalable Generative Model Control for High-Quality Multimodal Synthesis
… networks, have recently transformed foundational image synthesis tasks. However, challenges remain in designing generative models that are best suited for real-world applications and in improving their generalization capabilities across downstream tasks. This thesis addresses these challenges …
-
From heritage BIM towards an ‘echo-based’ modelling approach: developing a new paradigm for the digital creation of lost architectural heritage
… of existing heritage, its application to buildings that no longer physically exist remains limited. These cases often lack measurable or visual records, requiring novel methods to construct credible and authentic digital representations based on intangible data. This study aims to …
-
Grounding in multimodal foundation models: evaluating and improving modality-specific reasoning and generation
Multimodal foundation models aim to integrate information across vision, audio, and language, yet current systems often fail to ground their outputs in the modality that actually contains the relevant evidence. Instead, they tend to rely on dominant priors, particularly textual cues or vision …
-
Improving Semantic Precision in Text-to-Image Diffusion Models via Latent-Space Optimization and Semantically-Parsed Evaluation
Text-to-image diffusion models can produce visually impressive images from natural-language prompts, but they often fail to satisfy the detailed semantic constraints expressed in compositional prompts. Typical failure modes include omitted objects, merged entities, incorrect quantities, incorrect …
-
Towards Secure and Privacy-Preserving Machine Learning Systems
… applications, including healthcare, finance, autonomous systems, and critical infrastructure. While these models have delivered remarkable benefits and transformed numerous industries, they remain inherently vulnerable to a variety of security and privacy threats. Given their growing role in …
Page 1 of 2