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 59 for “"Generative modeling"”.

  1. Generative Modeling with Guarantees

    … focusing on improving the reliability of generative models while preserving their flexibility. First, we propose a framework that enables the generation of text conditionally using hard constraints, allowing users to specify certain elements in advance while leaving others open for the …

    mit Repository record for Generative Modeling with Guarantees (opens in a new tab)

  2. Probabilistic generative modeling of speech

    … speech synthesis also benefits from joint modeling. This thesis proposes a probabilistic generative model for speech called the Probabilistic Acoustic Tube (PAT). The highlights of the model are threefold. First, it is among the very first works to build a complete probabilistic model for …

    uiuc Repository record for Probabilistic generative modeling of speech (opens in a new tab)

  3. Generative modeling of sequential data

    … thesis, we investigate various approaches for generative modeling, with a special emphasis on sequential data. Namely, we develop methodologies to deal with issues regarding representation (modeling choices), learning paradigm (e.g. maximum likelihood, method of moments, adversarial training), …

    uiuc Repository record for Generative modeling of sequential data (opens in a new tab)

  4. Score Estimation for Generative Modeling

    Recent advances in score-based (diffusion) generative models have achieved state-of-the-art sample quality across standard benchmarks. Building on the remarkable property of these models in estimating scores, this thesis presents three core contributions: 1) new objectives to reduce score …

    mit Repository record for Score Estimation for Generative Modeling (opens in a new tab)

  5. Generative modeling of dynamic visual scenes

    Modeling visual scenes is one of the fundamental tasks of computer vision. Whereas tremendous efforts have been devoted to video analysis in past decades, most prior work focuses on specific tasks, leading to dedicated methods to solve them. This PhD thesis instead aims to derive a probabilistic …

    mit Repository record for Generative modeling of dynamic visual scenes (opens in a new tab)

  6. Generative modeling using the sliced Wasserstein distance

    Generative adversarial nets (GANs) are very successful at modeling distributions from given samples, even in the high-dimensional case. However, their formulation is also known to be hard to optimize and often unstable. While the aforementioned problems are particularly true for early GAN …

    uiuc Repository record for Generative modeling using the sliced Wasserstein distance (opens in a new tab)

  7. Generative modeling of interactive and reactive digital humans

    Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01

    uiuc Repository record for Generative modeling of interactive and reactive digital humans (opens in a new tab)

  8. Some advances in Bayesian inference and generative modeling

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms

    uiuc Repository record for Some advances in Bayesian inference and generative modeling (opens in a new tab)

  9. The Synthetic Data Vault : generative modeling for relational databases

    … Synthetic Data Vault (SDV), a system that builds generative models of relational databases. We are able to sample from the model and create synthetic data, hence the name SDV. When implementing the SDV, we developed an algorithm that computes statistics at the intersection of related database …

    mit Repository record for The Synthetic Data Vault : generative modeling for relational databases (opens in a new tab)

  10. Generative modeling of the tumor microenvironment : deconvolution, completion, and integration

    … correspondences. This dissertation develops generative modeling methods for each of these three problems. We introduce BayesTME, a Bayesian framework for deconvolving aggregated spatial transcriptomics measurements without requiring paired single-cell references. BayesTME models spot-level …

    texas Repository record for Generative modeling of the tumor microenvironment : deconvolution, completion, and integration (opens in a new tab)

  11. Theoretical Foundations of Flow-based Methods for Sampling and Generative Modeling

    … map. This construction is applicable to both generative modeling and variational inference; when the map is invertible, one can also estimate the density of the target measure by evaluating the density of the pushforward of the source distribution under the inverse transport map. Over the past …

    mit Repository record for Theoretical Foundations of Flow-based Methods for Sampling and Generative Modeling (opens in a new tab)

  12. Learning to draw vector graphics : applying generative modeling to font glyphs

    … In this work, we explore the applications of generative modeling to the design of vectorized drawings, with a focus on font glyphs. We establish a data-driven approach for creating preliminary graphics upon which designers can iterate. To accomplish this, we present an end-to-end pipeline for …

    mit Repository record for Learning to draw vector graphics : applying generative modeling to font glyphs (opens in a new tab)

  13. Developing frameworks for an equitable future: from building decarbonization to generative modeling.

    … building decarbonization policy and generative modeling. Part 1 - Equitable building decarbonization Buildings significantly contribute to global carbon emissions, necessitating urgent decarbonization to meet 2050 climate targets. The U.S. strives for net-zero emissions by 2050, …

    mit Repository record for Developing frameworks for an equitable future: from building decarbonization to generative modeling. (opens in a new tab)

  14. New tools for Bayesian optimal experimental design and kernel-based generative modeling

    … learning: optimal experimental design and generative modeling. Optimal experimental design (OED) is important to model development for science and engineering applications and beyond, especially when only a small number of observations can be taken or experiments performed, due to resource …

    mit Repository record for New tools for Bayesian optimal experimental design and kernel-based generative modeling (opens in a new tab)

  15. Two approaches to robust hand pose estimation : generative modeling and semantic relations

    … errors through a pipeline, we turn to generative modeling methods for hand pose estimation and present an inverse-graphics approach implemented in a probabilistic programming language. Spurred by the lack of occlusion in hand image datasets, we present the MIT Partially Occluded Hands …

    mit Repository record for Two approaches to robust hand pose estimation : generative modeling and semantic relations (opens in a new tab)

  16. Towards a Unified Framework for Visual Recognition and Generation via Masked Generative Modeling

    … in computer vision. However, recognition and generative models are typically trained independently, which ignores the complementary nature of the two tasks. In this thesis, we present a unified framework for visual data recognition and generation via masked generative modeling, and further …

    mit Repository record for Towards a Unified Framework for Visual Recognition and Generation via Masked Generative Modeling (opens in a new tab)

  17. Variational Autoencoders for Discovering Influential Latent Factors

    Generative modeling is increasingly being used to simulate or generate new unseen data instances by means of modeling the statistical distribution of data. Generative modeling falls under the broad area of representation learning, which aims to discover representations required for detecting …

    mit Repository record for Variational Autoencoders for Discovering Influential Latent Factors (opens in a new tab)

  18. 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 …

    mit Repository record for Structured Diffusion Processes in Deep Generative Models (opens in a new tab)

  19. Machine Learning Approaches to Multi-Modal Data Integration and Translation in Single-Cell Biology

    … In the first half, I develop methods based on generative modeling, representation learning and optimal transport to learn mappings between cells collected at different time points. In the second half, I develop methods based on generative modeling and representation learning to map between …

    mit Repository record for Machine Learning Approaches to Multi-Modal Data Integration and Translation in Single-Cell Biology (opens in a new tab)

Page 1 of 3