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 5 of 5 for “"Scalable AI"”.

  1. Towards Label-Efficient Learning: Exploiting Limited Labels and Abundant Unlabeled Data

    … a path toward building efficient, effective, and scalable AI systems by harmonizing limited labels, model capabilities, and the vast availability of unlabeled data. Experimental evaluations are conducted on publicly available datasets, including AG News, Yahoo! Answers, IMDB, Empathetic Dialogues, …

    uic

  2. Advancing Deep Learning Efficiency: From Specialized Co-Design to Automated Generation

    The explosive growth of artificial intelligence (AI) technologies, particularly large-scale deep learning models such as large language models and diffusion models, has intensified the demand for efficient full-stack inference solutions that effectively balance performance and costs. This work will …

    mit Repository record for Advancing Deep Learning Efficiency: From Specialized Co-Design to Automated Generation (opens in a new tab)

  3. Scalable foundation models

    … opportunities for artificial intelligence (AI) models. However, without scalable AI solutions (e.g., training algorithms, model architectures), much of this additional compute and annotation may be underutilized or yield diminishing returns. Furthermore, as real-world applications demand …

    uiuc Repository record for Scalable foundation models (opens in a new tab)

  4. A geospatial deep learning framework for scalable hydrographic mapping

    … disaster management and environmental sustainability. In the United States, the National Hydrography Dataset (NHD) provides the authoritative spatial framework for surface water representation, yet its reliance on manual interpretation and rule-based workflows limits the timeliness and …

    uiuc Repository record for A geospatial deep learning framework for scalable hydrographic mapping (opens in a new tab)

  5. Toward Transformer-based Large Energy Models for Smart Energy Management

    … developed to outperform in-situ models trained on individual buildings. To this end, we investigated and compared three candidate multi-variate Transformer architectures, utilizing both zero-shot and fine-tuning strategies, with data from 1,014 buildings. The results, evaluated across …

    vt Repository record for Toward Transformer-based Large Energy Models for Smart Energy Management (opens in a new tab)