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 15 of 15 for “"Multimodal Large Language Model"”.

  1. Latent Region-Wise Image Composition Using Multimodal Large Language Model

    Recent advances in text-to-image generative models, particularly latent diffusion models and more recent rectified-flow-based variants, have substantially improved the ability to synthesize images from textual prompts. Notably, models such as IP-Adapter provide effective image-prompt conditioning …

    ottawa-retro Repository record for Latent Region-Wise Image Composition Using Multimodal Large Language Model (opens in a new tab)

  2. Video Understanding with Attention Encoder and Multimodal Large Language Model

    … increasingly significant with the emergence of Multimodal Large Language Models (MLLMs). While MLLMs have demonstrated significant promise, effectively capturing and reasoning about complex temporal dynamics and object-level interactions in videos remains an active area of research. This project …

    auckland-tech Repository record for Video Understanding with Attention Encoder and Multimodal Large Language Model (opens in a new tab)

  3. Improving Vulnerable Road Users' Safety Through Computer Vision-Based Crossing Direction Prediction And Multimodal Large Language Model-Based Accident Scene Description

    … prediction and presents VRU-Accident, a large-scale benchmark enabling systematic assessment of multimodal large language models (MLLMs) in understanding accident scenarios involving VRUs. First, the proposed framework leverages multi-modal cues, including 3D pose estimation and …

    ucf Repository record for Improving Vulnerable Road Users' Safety Through Computer Vision-Based Crossing Direction Prediction And Multimodal Large Language Model-Based Accident Scene Description (opens in a new tab)

  4. AI-Aware and QoE-Driven Adaptive Transport for Real-Time Applications

    … interactive video streaming, cloud gaming, and multimodal large language model (MLLM) assistants—require low-latency, reliable delivery over highly variable wireless networks. Yet current transport and application mechanisms are often optimized in isolation: HTTP-based streaming introduces …

    concordia Download PDF for AI-Aware and QoE-Driven Adaptive Transport for Real-Time Applications (opens in a new tab)

  5. Post-Disaster Damage Assessment Using Deep Learning with Surrogate Data

    … pipeline that leverages vision foundation models to enable weakly supervised infrastructure damage localization from noisy ground-view imagery; and (iii) SeismoMind, a multimodal large language model framework for zero-shot damage assessment that achieves performance comparable to …

    gatech Repository record for Post-Disaster Damage Assessment Using Deep Learning with Surrogate Data (opens in a new tab)

  6. Efficient Knowledge Transfer and Adaptation for Speech and Beyond

    … learning, parameter-efficient adaptation, and multimodal modeling. First, we provide a comprehensive framework for class-incremental spoken language understanding, allowing models to incrementally learn new intents and entities while retaining previously acquired knowledge. Using knowledge …

    trento Repository record for Efficient Knowledge Transfer and Adaptation for Speech and Beyond (opens in a new tab)

  7. Development of Mobile Robot Architectures for Person Detection, Tracking, and Search

    … thesis presents three main contributions: 1) a multimodal person detection architecture that introduces Temporal Invariant Multimodal Contrastive Learning (TimCLR), which learns person representation that are invariant under intraclass variations through unsupervised learning; 2) a person …

    toronto-retro Repository record for Development of Mobile Robot Architectures for Person Detection, Tracking, and Search (opens in a new tab)

  8. Personalized and adaptive therapeutic music generation from biosignals using knowledge-guided multimodal large language models

    Multimodal generative models are reshaping digital therapeutics by enabling real-time synthesis of personalized content aligned with a user’s physiological and affective state. However, existing systems remain fragmented across modalities and often lack a unified framework that can jointly …

    utc Repository record for Personalized and adaptive therapeutic music generation from biosignals using knowledge-guided multimodal large language models (opens in a new tab)

  9. GlitchAgent: Detecting Video Game Glitches from Gameplay Videos

    … The videos are annotated with detailed, natural-language glitch descriptions and precise temporal timestamps, created through a semi-automated pipeline leveraging Multimodal Large Language Models (MLLMs) and human validation. Second, we propose GlitchAgent, a multi-stage framework for open-ended …

    vt Repository record for GlitchAgent: Detecting Video Game Glitches from Gameplay Videos (opens in a new tab)

  10. Contagious conspiracies: unmasking the role of conspiracy theories in online anti-vaccination communities

    … with a discourse analysis conducted by a multimodal large language model (LLM), this dissertation addresses this gap by investigating the role conspiracy theories play in the functionality and communicative practices of online anti-vaccination communities. Grounded in the theoretical …

    colostate Repository record for Contagious conspiracies: unmasking the role of conspiracy theories in online anti-vaccination communities (opens in a new tab)

  11. Perceptual quality assessment and enhancement of visual media using generative priors

    … novel datasets, objective quality models, and generative techniques—for assessing and enhancing the perceptual quality of visual media in the HDR-UGC era. The first part of this work establishes the data and algorithmic foundations for HDR-UGC video quality assessment. We begin by …

    texas Repository record for Perceptual quality assessment and enhancement of visual media using generative priors (opens in a new tab)

  12. Overcoming visual data scarcity with synthetic examples

    It is not news that deep networks with large numbers of parameters can easily fit to visual recognition tasks on large labeled datasets and generalize reasonably well. This task however becomes hard with few training data. Also challenging are scenarios where generalization is expected across test …

    bu Repository record for Overcoming visual data scarcity with synthetic examples (opens in a new tab)

  13. Learning vision language models from a messy and unstructured world

    … collect data, annotate the data and fit your model to the data. However, this paradigm is slowly running out of steam. As models scale, they demand substantially more annotated data, with finer granularity and richer semantic concepts. The cost of annotation is rising, yet even our largest …

    texas Repository record for Learning vision language models from a messy and unstructured world (opens in a new tab)

  14. Learning-Based Control and Tactile Perception for Robotic Systems

    … to track those trajectories under disturbances, modeling errors, and embodiment constraints. The reliability of the overall system is bounded by the weakest of these three loops, yet the corresponding research communities have, by and large, developed their methods in isolation. This dissertation …

    washington Repository record for Learning-Based Control and Tactile Perception for Robotic Systems (opens in a new tab)

  15. Velké jazykové modely pro vyhledávání v dopravních videích

    … s využítím multimodálních velkých jazykových modelů (MLLM) a souvisejících technologií, konkrétně multimodálních embedovacích modelů, přičemž oba typy modelů v nedávných letech zaznamenaly rychlý rozvoj. Systém je vytvořen tak, že podporuje výběr mezi více modely obou typů, čímž umožňuje …

    brno-tech Repository record for Velké jazykové modely pro vyhledávání v dopravních videích (opens in a new tab)