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 41 for “"Semantic Alignment"”.
-
Visual-Linguistic Semantic Alignment: Fusing Human Gaze and Spoken Narratives for Image Region Annotation
… and visual question answering depend heavily on semantic image region annotation. However, improvements in image region annotation are limited because of our inability to understand how humans, the end users, process these images and image regions. In this work, we expand a framework for …
-
Video Comprehension Score (VCS): A Metric for Long-Form Video Description Evaluation
… fail to capture the long-range chronology and semantic alignment essential for long-form descriptions. An effective evaluation metric for long-form descriptions must (i) assess global thematic alignment, (ii) measure local semantic alignment, and (iii) evaluate chronological alignment while …
-
Improving Semantic Precision in Text-to-Image Diffusion Models via Latent-Space Optimization and Semantically-Parsed Evaluation
… 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 attribute binding, and leakage of one entity's attributes onto another. This thesis studies the …
-
Semantic enrichment of database columns using generative language models for advanced query searches
… accuracy improvements. Results indicate improved semantic alignment when comparing generated descriptions to ground truth over column names alone and improved scores for established work.
-
ADVANCING VISION-LANGUAGE PRETRAINING: UNIFIED ARCHITECTURES AND IMPROVED GROUNDING ABILITIES
… challenges remain in achieving fine-grained semantic alignment and efficient processing of temporal dynamics in video. Addressing these issues, recent innovations have introduced Object-aware Transformers, which enhance video-language alignment by incorporating object representations and …
-
Semantic Fidelity in Specialized Domains: Advancing Language Models through Adaptive Learning, Collective Reasoning, and Consensus Evaluation
… domain-specific representations, generating semantically faithful and comprehensive outputs, and evaluating quality without extensive human annotation. This dissertation addresses these challenges through the unifying concept of semantic fidelity, defined as the preservation of intended …
-
SciRAG: A Retrieval-Focused Fine-Tuning Strategy for Scientific Documents
… Generation (RAG) framework that supports semantic alignment of mathematical expressions and technical language across large corpora. Experimental evaluations demonstrate that SciRAG achieves strong performance in scientific question answering and mathematical reasoning. Notably, the model …
-
Semantic Think-on-Graph (SemToG) : Enhancing GraphRAG through Semantic Community Detection
… on structural connectivity, often scattering semantically related entities across different communities and weakening the evidence provided to the LLM. We propose Semantic Think-on-Graph (SemToG), a semantic-aware extension of FastToG[7] that integrates node and relation embeddings directly …
-
Domain Adaptation and Privileged Information for Visual Recognition
… from the source and target distributions are semantically aligned and yet maximally separated. The second approach instead, extends adversarial learning to simultaneously maximize the confusion between source and target domains while achieving semantic alignment.;In complete absence of target …
-
Breaking Language Barriers: Reimagining Machine Translation as Style Transfer
… Large Language Model (LLM) embeddings to enhance semantic alignment and evaluation accuracy, deepening the work on transfer learning. This thesis also explores text compression through the development of Llamazip, a lossless compression algorithm that uses the predictive capabilities of LLMs. …
-
On Language as an Interface for Controlling Image Generation
… and manipulation. These models learn broad alignments between visual and textual representations, enabling flexible and general-purpose multimodal capabilities. However, using language as an efficient and robust interface for image generation remains challenging, with limitations in …
-
From Responses to Trajectories: Modeling the Development of Reflective Listening Skills
… markers of reflection quality, including semantic and affective alignment, along with patterns of language exchange between trainee and client. We find that reflective listening develops through systematic and measurable changes in language use over time. Trainee responses exhibit …
-
QLoRaX: Heuristic-Guided Fine-Tuning of LLaMA-2 for Domain Adaptation in Entrepreneurship
… epoch. The fine-tuned model demonstrated strong semantic alignment with human-written content, producing coherent, detailed, and contextually appropriate answers tailored to entrepreneurial questions. Through structured clustering and summary-based evaluation, we established a reliable framework …
-
Augmenting Video Retrieval: Leveraging Auxiliary Information to Enhance Retrieval Tasks
… information that could help facilitate alignment between modalities. Starting from cross-modal learning techniques, this thesis investigates how auxiliary information derived from videos and texts can improve retrieval performance by enhancing semantic alignment.<br/>The first …
-
Manipulation strategies of different objects applied to industrial settings - Identification of Objects and 6D Pose Estimation
… exhibits excellent generalization ability in semantic alignment, appearance consistency, and geometric compatibility, achieving an accuracy of 97% in challenging simulation scenarios. This study emphasizes the importance of SAM- 6D for 6D pose estimation in industrial applications where …
-
Understanding how Language Models Learn Under Constrained or Noisy Settings
… may matter more than the objective’s semantic alignment. The second study focuses on the internal structure of input tokens. Motivated by psycholinguistic findings, we test whether models can learn effectively from inputs with only partial character information. Results show that …
-
FullFlow: Towards Unified Text–Image Generation and Understanding
… rich visual structure, object relations, and semantic alignment between images and language. Yet this knowledge is exposed almost entirely through one direction of use. A prompt can become an image, but the same model cannot naturally run the process in reverse: given an image, it cannot …
-
ChatClothes: An AI-Powered Virtual Try-On System
… refinement. This prompt-based guidance enhances semantic alignment and enables intuitive user control beyond predefined attribute labels. To improve structural consistency and detail fidelity in image synthesis, this work introduces Low-Rank Adaptation (LoRA) for fine-tuning the original …
-
Explainability and Efficiency in Fuzzy Logic Systems: Frameworks for Temporal Classification, Monotonicity, and Hybrid Predictive Modeling
… novel frameworks addressing temporal modelling, semantic consistency, and hybrid inference. The work demonstrates that fuzzy systems can achieve semantic alignment with domain knowledge without compromising effectiveness. Key contributions include: The Optimized Time Series Interval Type-2 Fuzzy …
Page 1 of 3