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 6 of 6 for “"Parameter-Efficient Tuning"”.

  1. Parameter-Efficient Tuning as a Response to Corporate Capture in Natural Language Processing

    … from within the research community. We develop a parameter-efficient tuning (PET) method, prefix-propagation, ideal for long-document models. Before the introduction of our method, long document models interfaced poorly with PET. By using prefix-propagation, PET performance on classification tasks …

    queens Repository record for Parameter-Efficient Tuning as a Response to Corporate Capture in Natural Language Processing (opens in a new tab)

  2. Automatic Depression Assessment using Deep Learning Techniques

    … advances in pretrained large language models and parameter-efficient tuning techniques to effectively learn with limited data. Using speech and spoken text extracted from clinical interviews, our resultant models achieve new state-of-the-art performance results on a benchmark depression dataset …

    queens Repository record for Automatic Depression Assessment using Deep Learning Techniques (opens in a new tab)

  3. Intelligent Inside Threat Detection Framework Based on Digital Twin, Transformer Variant Models, and Transfer Learning

    … F1-score, and AUC, while being computationally efficient. To overcome challenges like data privacy and resource costs, we introduced FedITD, a Federated Parameter-Efficient Tuning (PETuning) framework with Federated Learning (FL) and Transfer Learning. This framework allows for decentralized …

    ottawa-retro Repository record for Intelligent Inside Threat Detection Framework Based on Digital Twin, Transformer Variant Models, and Transfer Learning (opens in a new tab)

  4. Prior knowledge-driven model pre-training and fine-tuning for ophthalmic image analysis

    … and the inefficiency of conventional fine-tuning strategies for large pre-trained models (LPMs). This thesis addresses these challenges by developing and evaluating novel pre-training and fine-tuning frameworks tailored for ophthalmic imaging. We first establish a strong and reproducible …

    ubc Repository record for Prior knowledge-driven model pre-training and fine-tuning for ophthalmic image analysis (opens in a new tab) Download PDF for Prior knowledge-driven model pre-training and fine-tuning for ophthalmic image analysis (opens in a new tab)

  5. Enhancing language models for telecom networks using retrieval-augmented generation: A pipeline for telecom-specific QA system

    … and proprietary LLMs available, where their parameter size can vary from a few billion to several trillion parameters. However, there are limitations of general-purpose pre-trained LLMs in handling domain-specific tasks, especially in the telecommunication domain. Challenges such as the …

    regina Repository record for Enhancing language models for telecom networks using retrieval-augmented generation: A pipeline for telecom-specific QA system (opens in a new tab)

  6. Enhancing Foundation Models with Self-Guided Techniques: From Attention to Adapters to Agents

    … leads to prohibitive computational costs; (2) inefficient adaptation strategies that require heavy supervision and resources, hindering use in resource-constrained environments; and (3) limited capabilities in handling complex tasks, such as automated hardware code generation and multi-agent …

    gatech Repository record for Enhancing Foundation Models with Self-Guided Techniques: From Attention to Adapters to Agents (opens in a new tab)