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 29 for “"multimodal reasoning"”.
-
Multiagent debate among vision-language models improves multimodal reasoning
We propose a framework for improving the multimodal reasoning capabilities of vision-language models through multiagent debate, where multiple models engage in a structured debate process, taking opposing perspectives and exchanging arguments about a given multimodal input containing text and …
-
Generalizable Adaptation for Vision-Language Models
Vision-Language Models (VLMs) and Multimodal Large Language Models (MLLMs) have recently emerged as powerful frameworks for learning joint representations across visual and textual modalities. These models enable a wide range of applications, including visual recognition, multimodal reasoning, and …
-
Agentic Multimodal Systems to Enhance Radiology Decision Support for Report Generation and Visual Question Answering
… question answering (RVQA) are two impactful multimodal tasks that can facilitate clinical documentation and enable interactive decision-making. Despite recent progress in multimodal large language models (MLLMs), current systems remain limited by insufficient interpretability and …
-
From contextual understanding to cognitive adaptation : multimodal AI for intelligent and adaptive multimedia systems
… be continuously optimised. Despite advances in multimodal machine learning, contemporary media decision systems remain largely perception-driven, operating on surface-level cues without structured reasoning over semantic meaning, narrative organisation, and viewer cognitive state. Addressing …
-
Towards Multimodal Scene Graph Generation Approaches to Video Understanding
… of Large Language Models (LLMs) for scene graph reasoning. To this end, three novel datasets and corresponding approaches are introduced. First, the ASPIRe dataset incorporates interactivity annotations and leverages the Hierarchical Interlacement Graph (HIG) for hierarchical temporal modeling, …
-
Artificial Intelligence (AI)-based Semantic Communications with Multimodal Data: Framework and Implementation
… existing works in this area either focus on multimodal approaches only and omit context-aware recovery or embed it in cross-modal settings, such as audio-to-video, rather than providing a unified, modality-agnostic method. These works also impose substantial architecture redesigns for …
-
Advancing Generative Methods for Multimodal Data Analysis
… by developing novel generative frameworks for multimodal data reconstruction, imputation, and interaction prediction. In generative modeling, we focus on capturing structural and causal dependencies in sparse biological systems. We first introduce CausalGeD, a causality-aware diffusion …
-
AI-Powered Multimodal Tour Guide: Enhancing Cultural Tourism with Image Recognition, and Personalized Storytelling
… the design and evaluation of an AI-powered multimodal tour guide that uses image recognition and personalised storytelling to enhance cultural heritage experiences. Traditional approaches to learning about monuments rely on static plaques, generic tour content, or manual web searches, which …
-
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 …
-
Scalable Vision-Language Alignment with Generative Models
… an efficient control interface for perception, reasoning, and action. This dissertation advances a generative perspective that treats large autoregressive language models and text-conditioned diffusion models as an alignment engine—using scalable text and visual generation to bring perception …
-
Audo-Sight: Enabling Ambient Interaction for Blind and Visually Impaired Individuals
… assistive system that seamlessly integrates Multimodal Large Language Models (MLLMs) to provide expedient, context-aware interactions for Blind and Visually Impaired (BVI) individuals. Unlike traditional assistive devices, our system can respond adaptively to the user environment, providing …
-
Resource efficient distributed inference of deep neural networks for Edge AI
… image recognition, language understanding, and multimodal reasoning. However, executing these models efficiently on edge devices remains a major challenge due to their high computational, energy, and bandwidth demands. This dissertation presents a unified framework for resource-efficient …
-
Toward Self-Sustaining and Adaptive Cyber Defense: From Payload-Centric Detection to Multimodal, Graph-Based Approach
… Detection Systems (NG-IDS) toward adaptive, multimodal, and interpretable operation. It first addresses reproducibility gaps in packet-level benchmarking through standardized flow-to-packet transformation tools. Building on this foundation, it introduces novel packet-level representations …
-
Toward Self-Sustaining and Adaptive Cyber Defense: From Payload-Centric Detection to Multimodal, Graph-Based Approach
… Detection Systems (NG-IDS) toward adaptive, multimodal, and interpretable operation. It first addresses reproducibility gaps in packet-level benchmarking through standardized flow-to-packet transformation tools. Building on this foundation, it introduces novel packet-level representations …
-
Toward Self-Sustaining and Adaptive Cyber Defense: From Payload-Centric Detection to Multimodal, Graph-Based Approach
… Detection Systems (NG-IDS) toward adaptive, multimodal, and interpretable operation. It first addresses reproducibility gaps in packet-level benchmarking through standardized flow-to-packet transformation tools. Building on this foundation, it introduces novel packet-level representations …
-
Representation Learning for Temporal Structure and Procedural Understanding in Video
… language-guided dense prediction and contextual multimodal reasoning. Cataract surgery is a rigorous setting because it follows an ordered workflow while showing substantial variation in anatomy, surgeon style, instrument motion, viewpoint, blur, and illumination. Unlabeled video is abundant, but …
-
Evaluating Vision-Language-Action Models in Robotic Manipulation: Performance, Implementation, and Comparison with Deterministic Systems
… effort and inflexibility through learned multimodal reasoning. However, their practicality in the real world and associated development costs remain largely unknown. This thesis presents a real-world comparison of a strong open-source VLA foundation model (OpenVLA-7B) against a fine-tuned …
-
Towards Grounded Visual Understanding in Vision–Language Models
… evaluation, supervision, representation, and reasoning. First, this thesis shows that existing benchmarks can overestimate grounded understanding because models may exploit dataset artifacts rather than visual evidence. To address this limitation, it develops more reliable and fine-grained …
-
Bias, Memorization, and Identity Fidelity in Generative Models
… progress in image synthesis, restoration, and multimodal reasoning. However, diffusion models and multimodal large language models (MLLMs) often exhibit undesirable behaviors, including social bias, training data memorization, and identity distortion, raising important concerns regarding …
Page 1 of 2