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 27 for “"Large Vision-Language Models"”.
-
Connecting Text and Charts Using Large Vision-Language Models
… documents. In this thesis, we propose two large vision-language model (LVLM)-based frameworks—a single-agent baseline and a multi-agent architecture—for automatically linking textual descriptions with their corresponding chart data. Both frameworks extract structured data from chart images …
-
Building Trustworthy AI: Uncertainty Quantification and Failure Detection in Large Vision-Language Models
… we explore uncertainty quantification in natural language generation (NLG) tasks, particularly in the context of large language models (LLMs). We introduce Contrastive Semantic Similarity, a Contrastive Language–Image Pre-training (CLIP) based feature extraction module, to measure semantic …
-
VIDEO UNDERSTANDING: THROUGH TEMPORAL LENS
… an automatic annotation approach that uses large vision-language models to capture temporal progressions, coupled with a contrastive learning objective to mitigate noise. For resource-constrained scenarios, we propose recurrent adapters with parameter-efficient training to better model …
-
Toward Causal Generative Modeling: From Representation Learning to Controllable Generation
… statistical patterns, current generative models often struggle to capture the underlying structural causal mechanisms of the data-generating process, leaving them vulnerable to shortcut learning and spurious associations. To achieve true generalizability and interpretability, artificial …
-
Developing object perception in the low data regime
… the utility of systems requiring strong supervision through large labelled datasets. To address this issue, this thesis develops methods to enable novel objects to be learnt with limited use of manually labelled data.</p> <p>First, we consider the problem of few-shot object detection, which is …
-
ADVANCEMENTS IN IMAGE SEGMENTATION: FROM SUPERVISED LEARNING TO ZERO-SHOT FOUNDATION MODELS
… segmentation is a fundamental task in computer vision with critical importance in biomedical imaging, environmental monitoring, and artificial intelligence. This dissertation investigates the evolution of segmentation methodologies across four major paradigms: traditional machine learning with …
-
CLOSED-LOOP SCALING: AUTONOMOUS IMPROVEMENT OF LLM AND LVLM REASONING
… exhaustion, sustaining the improvement of large language models (LLMs) and large vision--language models (LVLMs) demands a paradigm shift. This thesis proposes automatic scaling: a closed-loop framework in which models autonomously improve through their own computation via three layers. …
-
EFFORTS TOWARD TRUSTWORTHY MACHINE LEARNING: MITIGATING OVERCONFIDENCE, HALLUCINATION, AND MODALITY BIAS
… high-stakes domains. Despite strong performance, models remain prone to reliability issues such as overconfidence, hallucinations, and modality bias. This thesis addresses these challenges through post-hoc methods and targeted fine-tuning strategies. First, we mitigate overconfidence in …
-
Mutual exclusivity bias and spatial reasoning in Vision-Language Models
… rapid advancements in machine learning, enabling models to generalize beyond their training data, they still lag significantly behind the learning efficiency of young children. In this dissertation, we draw inspiration from developmental psychology, specifically children’s learning environments …
-
Advanced Methods for Remote Sensing Image Captioning
… captioning (IC) involves generating natural language descriptions for images, enabling machines to communicate their perception through language. This approach provides a flexible framework to convey diverse semantics. Despite significant advancements, IC systems face challenges in …
-
Generation and evaluation of semantic counterfactual explanations
… transitioning from research prototypes to large-scale deployments in healthcare, finance, security, and transportation. Despite their success, AI models often function as opaque black boxes, raising concerns about trust, adoption, and risk in high-stakes applications. Explainable AI (XAI) …
-
Advancing Structural and Textual Guidance in Medical Image Segmentation: A Journey from Fully Supervised to Weakly Supervised Learning
… of anatomical structures. While advanced models have achieved impressive per-pixel performance under fully supervised settings, ensuring fine-scale structural completeness remains a challenge, particularly for complex biomedical structures where coherence and integrity are critical. Fully …
-
An Empirical Study of Differences Between Human and AI Reasoning in Security-Related Tasks
Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) are increasingly deployed in security-related tasks that involve perception, reasoning, and decision making. Although these models achieve strong performance on many benchmarks, their reasoning processes, driven primarily by …
-
Towards Scalable and Label-Efficient Visual Perception with Vision Foundation Models
… remains a fundamental challenge in computer vision. Contemporary perception pipelines achieve strong performance on curated benchmarks, yet they rely heavily on dense supervision, fixed label spaces, and modality-specific assumptions, limiting their applicability in open, dynamic, and …
-
AdaptPrompt with Diffusion Set: A Unified Framework for Generalizable Deepfake Detection
… impressive performance, leveraging deep learning models to distinguish between real and synthetic content. However, recent developments in diffusion-based generative models and publicly available tools such as Stable Diffusion and DALL-E pose immediate challenges to existing detection techniques. …
-
Bridging Evidence and Uncertainty: From Explainable Weighting to Uncertainty Calibration in Fact Checking
… framework that calibrates the NEI decision of large vision-language models. Its Evidence-Grounded Reasoning module decomposes a claim into atomic facts, verifies each against retrieved multimodal evidence, and labels it as supported, not supported, or uncertain, which forces the model to reason …
-
Recognizing Object-Centric Attributes and Relations
… This dissertation aims to equip computer vision systems with this capability, empowering them to recognize object's attributes and relations to become more robust in handling real-world scene complexities. The thesis is structured into two main parts. The first part focuses on recognizing …
-
Toward Reliable Supervision for Foundation Models
Foundation models have made rapid progress in reasoning, alignment, and multimodal understanding, but their reliability critically depends on the quality of supervision used during learning. Such supervision may come from learned reward models, verifiable outcomes, expert models, the model itself, …
-
AI-assisted video data management for compositional and high-level queries
… as predicate compositions. Directly applying large vision-language models (VLMs) to every video can address some of these limitations, but doing so is prohibitively expensive at scale. In this dissertation, we present three systems that make compositional and high-level video queries easier to …
-
Prior-Informed Visual Enhancement and 3D Reconstruction under Challenging Illumination
… remain fundamental challenges in computer vision. Images captured under adverse illumination suffer from detail loss, amplified noise, and color shifts, degrading visual quality and hindering recognition, navigation, and scene understanding. Despite rapid progress, many LLIE pipelines still …
Page 1 of 2