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 232 for “"Foundation model"”.

  1. Robust foundation model for healthcare

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2026-02-19 without embargo terms

    uiuc Repository record for Robust foundation model for healthcare (opens in a new tab)

  2. Data curation for foundation model training

    … the amount of data available for training these models was often limited, research aimed on improving the way these relatively small amounts of data could be used. More recently, this focus has shifted from iteration on the algorithms to iteration on the data itself. Techniques such as data …

    texas Repository record for Data curation for foundation model training (opens in a new tab)

  3. Foundation Model for Single-Cell Omics

    … data. We develop versatile computational models capable of learning from large-scale data. The key innovation is a pretraining and transfer learning paradigm to construct foundation models tailored to single-cell analysis. We design self-supervised learning tasks to enable scalable …

    toronto-retro Repository record for Foundation Model for Single-Cell Omics (opens in a new tab)

  4. Effective and Efficient Graph Foundation Model

    … Inspired by the transformative impact of foundation models in natural language processing, this thesis explores the feasibility of developing a graph foundation model—a single, unified model capable of generalizing across diverse graph tasks and domains. Such a model would not only address …

    wustl Repository record for Effective and Efficient Graph Foundation Model (opens in a new tab)

  5. Building a foundation model for neuroscience

    … of robust and comprehensive computational models of brain function that generalize across diverse conditions, tasks, and individuals. Our work is motivated by the need for a large-scale foundation model in neuroscience--one that can go beyond the limitations of single-dataset approaches and …

    gatech Repository record for Building a foundation model for neuroscience (opens in a new tab)

  6. Human-centric trustworthy foundation model reasoning

    … Advancements in AI have given rise to language models (LMs) being increasingly adopted in assisting information understanding and communication for different task settings. However, the potential that LMs can serve in supporting human communication is still hindered by important issues. As …

    uiuc Repository record for Human-centric trustworthy foundation model reasoning (opens in a new tab)

  7. EFFICIENCY IN THE ERA OF FOUNDATION MODEL

    The era of foundation models has created unprecedented efficiency challenges across two critical dimensions: model efficiency and data efficiency. This thesis provides a comprehensive investigation of both dimensions, demonstrating that their combination offers the most practical path to deploying …

    nus Repository record for EFFICIENCY IN THE ERA OF FOUNDATION MODEL (opens in a new tab) Download file for EFFICIENCY IN THE ERA OF FOUNDATION MODEL (opens in a new tab)

  8. A Foundation Model for Microbial Growth Dynamics

    … spaces. To address this, we developed a foundation model for microbial growth dynamics that enables researchers to extract meaningful features from limited datasets. Our model learns lower-dimension embeddings that distill key characteristics from raw growth data, and this enhances …

    duke Repository record for A Foundation Model for Microbial Growth Dynamics (opens in a new tab) Embargoed until 2027-05-19

  9. Towards Foundation Model for Single-Cell Biology

    Thesis (Ph.D.)--Michigan State University. Statistics - Doctor of Philosophy, 2026

    msu Repository record for Towards Foundation Model for Single-Cell Biology (opens in a new tab)

  10. Efficient Multimodal Foundation Model Tuning For Hallucination Mitigation

    Over the past few years, multimodal foundation models have achieved remarkable progress in perception and understanding. However, two challenges limit their reliability: (1) dependence on offline training, which in most real-world settings requires large volumes of labeled data and, as a result, …

    uab Repository record for Efficient Multimodal Foundation Model Tuning For Hallucination Mitigation (opens in a new tab)

  11. Towards Developing a Foundation Model for Agricultural Vision

    … vision have enabled the development of powerful models for natural image understanding. However, adapting these advances to domain-specific tasks in agriculture—characterized by limited annotated data, high visual complexity, and domain shift—remains an open challenge. This thesis aims to address …

    calgary Repository record for Towards Developing a Foundation Model for Agricultural Vision (opens in a new tab)

  12. A Foundation model for the practice of school psychology

    … philosophical, theoretical, and practical foundations of school psychology yielded reasons for the crisis in the profession. The underlying assumptions of externalism and resulting faulty notions about objectivity and value neutrality were shown to be major contributors to the problems of …

    northern-iowa Repository record for A Foundation model for the practice of school psychology (opens in a new tab)

  13. Effective Model Deployment and Data Curation for Foundation Model Development

    While scaling—both in terms of model size and dataset volume—has driven many of the recent breakthroughs in AI, this increasingly larger-scale development trajectory faces emergent challenges not seen in traditional small-scale supervised learning setting. On model side, the exponential growth in …

    washington Repository record for Effective Model Deployment and Data Curation for Foundation Model Development (opens in a new tab)

  14. Revealing and Mitigating Privacy Leakage in Distributed and Foundation Model Learning

    … by keeping raw data local while sharing only model updates or intermediate representations. However, numerous studies have exposed seemingly devastating vulnerabilities, suggesting these privacy-preserving systems fail to serve their purpose. This dissertation systematically reassesses privacy …

    toronto-retro Repository record for Revealing and Mitigating Privacy Leakage in Distributed and Foundation Model Learning (opens in a new tab)

  15. Semantically-Guided Image Synthesis: Augmenting VAE Decoders with Foundation Model Representations

    … επιπέδου σημασιολογική πληροφορία από Vision Foundation Models(VFMs). Κεντρικό στοιχείο της προσέγγισής μας είναι η προσαρμογή του ελαφρού συνελικτικού σημασιολογικού συμπιεστή που εισήχθη στο πλαίσια της δουλειάς του REGLUE. Ενώ το REGLUE χρησιμοποιεί αυτό το υποσύστημα για να ενσωματώσει …

    athens Repository record for Semantically-Guided Image Synthesis: Augmenting VAE Decoders with Foundation Model Representations (opens in a new tab)

  16. Towards a foundation model for multi-modal and hyperspectral geospatial data

    Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-08-01

    uiuc Repository record for Towards a foundation model for multi-modal and hyperspectral geospatial data (opens in a new tab)

  17. MASK-FREE SHADOW REMOVAL VIA FREQUENCY DISCRIMINATION AND FOUNDATION MODEL FUSION

    … and CNN based network. Specifically, a foundation model based on ConvNextV2 network learns the local texture, restores realistic lightning and a tweaked Vision Transformer called FFTFormer removes global shadow artifacts by separating it based on Fast Fourier Transform(FFT) . In …

    mcmaster Repository record for MASK-FREE SHADOW REMOVAL VIA FREQUENCY DISCRIMINATION AND FOUNDATION MODEL FUSION (opens in a new tab)

Page 1 of 12