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 4 of 4 for “"Multimodal Reasoning"”.

  1. 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 …

    vt Repository record for Artificial Intelligence (AI)-based Semantic Communications with Multimodal Data: Framework and Implementation (opens in a new tab)

  2. 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 …

    umkc Repository record for Resource efficient distributed inference of deep neural networks for Edge AI (opens in a new tab)

  3. Instruction Mining from Images: Constructing a Synthetic Dataset for Multimodal Learning

    … και των πολυτροπικών μοντέλων όρασης–γλώσσας (Multimodal Large Language Models – MLLMs) έχει οδηγήσει στην ανάπτυξη συστημάτων ικανών να συνδυάζουν οπτική και γλωσσική πληροφορία για την εκτέλεση σύνθετων εργασιών συλλογισμού, κατανόησης εγγράφων, OCR, οπτικού διαλόγου και multimodal

    athens Repository record for Instruction Mining from Images: Constructing a Synthetic Dataset for Multimodal Learning (opens in a new tab)

  4. CLOSED-LOOP SCALING: AUTONOMOUS IMPROVEMENT OF LLM AND LVLM REASONING

    … via three layers. Inference-time scaling treats reasoning as search guided by self-evaluation. Training-time scaling internalizes search-discovered knowledge into parameters through iterative preference alignment. Architectural grounding provides structural foundations for sustainable scaling. …

    nus Repository record for CLOSED-LOOP SCALING: AUTONOMOUS IMPROVEMENT OF LLM AND LVLM REASONING (opens in a new tab)