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 240 for “"Generative models"”.
-
Listening with generative models
… contemporary tools to build and apply rich generative models that describe what we hear. First, I present a hierarchical Bayesian auditory scene synthesis model to address the perceptual organization of sound into sources and events. We aimed to bridge between classical auditory scene …
-
Fine-tuning generative models
Deep generative models have emerged as a powerful modeling paradigm for making sense of large amounts of unlabeled real-world data. In particular, the representations produced by these models have proven to be useful both in improving human understanding of the factors of variation in the original …
-
Generative Models for Computer Vision
… build robust computer vision algorithms, scene models are necessary that are capable of capturing various aspects of the data at the same time. These models should be fairly simple, but capable of adapting to the data. Flexible models, as defined in the machine learning community, are minimally …
-
Exploring knowledge in generative models
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms
-
Multimodal generative models for storytelling
… thinking and requires a constant flow of ideas. Generative models have recently gained momentum thanks to their ability to identify complex data's inner structure and learn efficiently from unlabeled data [34]. Natural language generation (NLG) for storytelling is especially challenging because …
-
On Physics-Inspired Generative Models
Physics-inspired generative models such as diffusion models constitute a powerful family of generative models. The advantages of models in this family come from relatively stable training process and high capacity. A number of possible improvements remain possible. In the thesis, we will first …
-
Generative Models Driven Graph Outlier Detection
… the complex non-Euclidean graph data. Recently, generative models have exhibited extraordinary performance on image and language data, but their capabilities in graph outlier detection remain largely underexplored. In this dissertation, I systematically investigate the capabilities of generative …
-
Deep Generative Models and Biological Applications
… in a wide variety of applications. </p><p>Generative models provide an excellent manipulation method for training from rich available unlabeled data set and sampling new data points from underlying high-dimensional probability distributions. </p><p>The recent proposed Variational …
-
Deep generative models for speech editing
Generative models are very useful for generating and modifying natural-sounding speech in various speech processing tasks such as speech synthesis, speech enhancement, and voice conversion. There are two ways that the generative models can help in naturalness for speech processing. The first way is …
-
Modeling Biomolecular Interactions with Generative Models
… to this problem, modeling structures with a new generative paradigm and tailoring the neural architectures and learning tasks to the specific challenges that arose. These ideas combined with significant engineering efforts led us to develop a class of open-source models from DiffDock to the …
-
Efficient Generative Models for Visual Synthesis
While current visual generative models produce high-quality outputs, they suffer from significant computational costs and latency, limiting their applicability in interactive settings. In this dissertation, we introduce a suite of techniques designed to enhance the efficiency of generative models …
-
Generative Models for Domain-Specific Summarization
This project evaluates the performance of generative models of summarization in aviation safety domain. Models such as DaVinci, Text-DaVinci-003, and GPT-3.5-Turbo were analyzed in both their zero-shot learning and fine-tuned performance against state-of-the-art models. In zero-shot learning, …
-
Learning Generative Models Using Structured Latent Variables
… knowledge to standard deep learning models. This domain-specific knowledge is used to specify meaningful latent representation with structure, which forces the model to generalize better under certain scenarios. For example, a generative model with latent gating variables that will …
-
Improve the efficiency of conditional generative models
Deep generative models have undergone significant advancements, enabling the production of high-fidelity data across various fields, including computer vision and medical imaging. The availability of paired annotations facilitates a controllable generative process through conditional generative …
-
Generative models for problems in imaging science
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-12-04 without embargo terms
-
Generative models for predictive UI design tools
… be arranged and styled. This paper introduces a generative model approach to predictive design for mobile UI layouts. Given a partial UI design, the model predicts the next UI element that should be added to the layout. Moreover, the model can be used queried multiple times in succession to …
-
Deep generative models via explicit Wasserstein minimization
This thesis provides a procedure to fit generative networks to target distributions, with the goal of a small Wasserstein distance (or other optimal transport costs). The approach is based on two principles: (a) if the source randomness of the network is a continuous distribution (the …
-
Adversarial attacks and defenses for generative models
… studies vulnerabilities of Machine learning models that make them susceptible to attacks. The attacks are inflicted by carefully designing a perturbed input which appears benign, but fools the models to perform in unexpected ways. To date, most work in adversarial attacks and defenses has …
-
Structured Diffusion Processes in Deep Generative Models
Diffusion generative models have emerged as a powerful, versatile, and elegant generative modeling framework for diverse data modalities. However, the high computational cost of inference relative to other frameworks remains a chief limitation of such models. At the same time, the design space of a …
-
Data Attribution: From Classifiers to Generative Models
… in such regimes require training thousands of models, which makes them impractical for large models or datasets. Moreover, existing methods are often tailored to the supervised learning setting, and are not well-defined for generative models. In this thesis, we introduce TRAK (Tracing with the …
Page 1 of 12