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 454 for “"Fine-tuning"”.
-
Fine-tuning generative models
… Instead, we propose various methods of fine-tuning pre-trained generative models to achieve these goals, and evaluate these methods quantitatively on few-shot classification and interpretability tasks.
-
Being Human: Fine-Tuning Moral Naturalism
… of theory in morality, cannot accommodate the fineness of morally good deeds. Turning to the work of writers in the Wittgensteinian tradition I show how ethics is dependent on a sense of the human condition, rather than on a theory of human nature. In other words, to explain the fineness of …
-
ZIPRO1: Fine Tuning Proliferation in Discrete Cell Populations
<p>Zipro 1 is a zinc finger transcription factor that has a restricted pattern of expression in several tissues. The main cells expressing Zipro1 are proliferating cells from epidermal lineages. This includes the cerebellar granule cells (GCs), nasal epithelia and dermal papilla. Through gene …
-
Fine-tuning Boltz for Antibody-Antigen Binding Prediction
… approaches often fall short in capturing the fine-grained features that drive binding specificity in antibody and antigens. This thesis evaluates multiple strategies for improving predictive performance. First, we investigate a custom multiple sequence alignment (MSA) experiment. Standard …
-
Investigating Fine-Tuning of Language Models for Multiple-Choice Questions
… method of improving the performance of LLMs is fine-tuning, wherein a model is additionally trained on data from a specified distribution or subject area. We specifically investigate training data properties related to positional bias in fine-tuned language model performance on correctly …
-
Fine-tuning a domain-specific language model for truss structural analysis
This research investigates the feasibility of fine-tuning a domain-specific vison-language and large-language for truss structural analysis. General-purpose AI models often struggle with engineering-specific problems due to insufficient domain knowledge. To address this, we propose a hybrid …
-
Methods for Latent Space Interpretation via In-the-loop Fine-Tuning
… qualities that make two item similar. Leveraging fine-tuning mechanisms, dimension reduction algorithms and Sparse Autoencoders (SAEs), this work surveys state-of-the-art techniques to visualize the latent space in highly interpretable dimensions. ConceptAxes, derived from these techniques, is a …
-
Optimizing Multi-Dimensional Efficiency of Foundation Models: From Fine-Tuning to Inference
… evaluation, and decision-making from fine-tuning to deployment scheduling. First, it introduces a multi-dimensional efficiency evaluation framework spanning runtime, GPU memory footprint, and energy consumption, demonstrating why single-metric optimization can be misleading. Second, it …
-
Trustworthy Federated Learning Systems: From Secure Distributed Training to Reliable Fine-tuning
Training and fine-tuning Deep Learning (DL) models require vast amounts of domain-specific data. However, this data is often distributed across different organizations and devices, restricted from direct sharing by privacy, ownership, and regulatory constraints. While Federated Learning (FL) …
-
Accelerating Distributed Deep Neural Network Training and Fine-Tuning Through Resource Interleaving
… distributed Machine Learning (ML) training and fine-tuning workloads quickly takes up a significant portion of iteration time. Yet state-of-the-art ML schedulers tend to ignore the communication pattern of ML jobs when placing workers on GPUs. This thesis advocates for communication-aware …
-
"fine-tuning" of ribosomal structure and functions by pseudouridylation and rna-protein interactions
<p>ABSTRACT</p> <p>"Fine-tuning" of ribosomal structure and functions by pseudouridylation and RNA-protein interactions</p> <p>by</p> <p>JUN JIANG</p> <p>AUGUST 2012</p> <p>Advisor: Prof. John SantaLucia Jr.</p> <p>Major: Chemistry (Biochemistry)</p> <p>Degree: Doctor of Philosophy</p> <p>Ribosomal …
-
QLoRaX: Heuristic-Guided Fine-Tuning of LLaMA-2 for Domain Adaptation in Entrepreneurship
<p>This thesis presents a study on the fine-tuning of large language models (LLMs) for domain-specific applications using limited data. We fine-tuned the LLaMA-2 (7B) model on a curated entrepreneurial dataset containing 3,545 human-written question-answer pairs, of which 3,095 were used for …
-
Evaluation and Enhancement of Qualitative Spatial Reasoning in LLMs via Symbolic Fine-Tuning
… εάν η αρχιτεκτονική του μπορεί να εκπαιδευτεί (fine-tuning) ώστε να εσωτερικεύσει τους κανόνες του Λογισμού Κύριων Κατευθύνσεων (Cardinal Direction Calculus- CDC). Η μεθοδολογία περιλαμβάνει μια εκτενή πειραματική μελέτη τριών φάσεων, χρησιμοποιώντας ένα σύνολο δεδομένων (ground truth) των …
-
Exploring Fine-Tuning Techniques for Removing Tamper-Resistant Safeguards for Open-Weight LLMs
… repurposed for malicious tasks via adversarial fine-tuning. In this paper, we evaluate the effectiveness of Tampering Attack Resistance (TAR), a safeguard designed to protect against such adversarial attacks, by exploring its resilience to full-parameter and parameter-efficient fine-tuning. Our …
-
The Effects of Pre-Training and Fine-Tuning CLIP with Domain-Specific Data
… to explore the possibility of pre-training or fine-tuning CLIP with Mercari’s data to improve its performance within Mercari’s data domain. We explore various training strategies to understand the effects of each and determine the most effective strategy. Our best-performing and most …
-
Domain Adaptation of LLMs for Materials Science: Dataset Curation, Fine-Tuning, and Evaluation Benchmark
… the thesis introduces a curated instruction-tuning dataset composed of diverse question-answer (QA) pairs drawn from various materials science sources such as textbooks, property databases, and expert forums. This dataset was used to fine-tune the LLaMA-3-8B-Instruct model, to create a …
-
Fine-tuning CLIP models for peripheral blood cell images retrieval based on morphological descriptions
This master's thesis explores the fine-tuning of Contrastive Language-Image Pre-training (CLIP) models for retrieving peripheral blood cell images based on morphological descriptions, aiming to assist hematologists in diagnostic processes. The study addresses the limitations of manual peripheral …
-
Fine���tuning the reduction potential of Cupredoxin proteins by altering secondary coordination sphere interactions
… that the Em of the cupredoxin azurin (Az) can be fine‐tuned in small, ~50 iii mV increments across a 500‐600 mV range simply by modifying hydrogen bonding and hydrophobic interactions in the secondary coordination sphere of the copper site. Surprisingly, this large range of achievable Em values …
-
Evaluating Adaptive Layer Freezing through Hyperparameter Optimization for Enhanced Fine-Tuning Performance of Language Models
… these models in specialized downstream tasks via fine-tuning. However, fine-tuning on small datasets can lead to overfitting and a lack of generalization. Generalization is crucial when deploying models that perform a sensitive tasks in a real world environment, as it dictates how well it performs …
Page 1 of 23