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 15 of 15 for “"Image generation models"”.

  1. Designing, learning, and utilizing dense reward for generative AI alignment

    … (RLHF) training of text and text-to-image generation models. We start from learning better dynamics and reward models for policy learning in offline model-based reinforcement learning (offline MBRL), from the angle of mitigating the mismatched dynamics/reward-model objectives. Built …

    texas Repository record for Designing, learning, and utilizing dense reward for generative AI alignment (opens in a new tab)

  2. Diffuse2Adapt: Controlled Diffusion for Synthetic-to-Real Domain Adaptation

    … alternative to annotating data. However, models trained on synthetic data often face a drop in performance when evaluated on real data due to the synthetic-to-real domain gap. Unsupervised domain adaptation (UDA) techniques attempt to leverage a set of unlabeled target data in various ways …

    jhu Repository record for Diffuse2Adapt: Controlled Diffusion for Synthetic-to-Real Domain Adaptation (opens in a new tab)

  3. Towards Secure and Privacy-Preserving Machine Learning Systems

    … adoption of increasingly sophisticated models across a broad range of real-world applications, including healthcare, finance, autonomous systems, and critical infrastructure. While these models have delivered remarkable benefits and transformed numerous industries, they remain inherently …

    wustl Repository record for Towards Secure and Privacy-Preserving Machine Learning Systems (opens in a new tab)

  4. Locating Knowledge in Vision-Language and Diffusion Models

    … examines the interpretability of vision-language models (VLMs) and image generation models, ascertaining where and how these models store world knowledge. An analysis of the embedding spaces of Vision-Language encoders and the hidden layers of diffusion models is conducted to understand how …

    tamu Repository record for Locating Knowledge in Vision-Language and Diffusion Models (opens in a new tab) Embargoed until 2027-08-01

  5. Locating Knowledge in Vision-Language and Diffusion Models

    … examines the interpretability of vision-language models (VLMs) and image generation models, ascertaining where and how these models store world knowledge. An analysis of the embedding spaces of Vision-Language encoders and the hidden layers of diffusion models is conducted to understand how …

    tamu Repository record for Locating Knowledge in Vision-Language and Diffusion Models (opens in a new tab) Embargoed until 2027-08-01

  6. Locating Knowledge in Vision-Language and Diffusion Models

    … examines the interpretability of vision-language models (VLMs) and image generation models, ascertaining where and how these models store world knowledge. An analysis of the embedding spaces of Vision-Language encoders and the hidden layers of diffusion models is conducted to understand how …

    tamu Repository record for Locating Knowledge in Vision-Language and Diffusion Models (opens in a new tab) Embargoed until 2027-08-01

  7. Locating Knowledge in Vision-Language and Diffusion Models

    … examines the interpretability of vision-language models (VLMs) and image generation models, ascertaining where and how these models store world knowledge. An analysis of the embedding spaces of Vision-Language encoders and the hidden layers of diffusion models is conducted to understand how …

    tamu Repository record for Locating Knowledge in Vision-Language and Diffusion Models (opens in a new tab) Embargoed until 2027-08-01

  8. Locating Knowledge in Vision-Language and Diffusion Models

    … examines the interpretability of vision-language models (VLMs) and image generation models, ascertaining where and how these models store world knowledge. An analysis of the embedding spaces of Vision-Language encoders and the hidden layers of diffusion models is conducted to understand how …

    tamu Repository record for Locating Knowledge in Vision-Language and Diffusion Models (opens in a new tab) Embargoed until 2027-08-01

  9. Locating Knowledge in Vision-Language and Diffusion Models

    … examines the interpretability of vision-language models (VLMs) and image generation models, ascertaining where and how these models store world knowledge. An analysis of the embedding spaces of Vision-Language encoders and the hidden layers of diffusion models is conducted to understand how …

    tamu Repository record for Locating Knowledge in Vision-Language and Diffusion Models (opens in a new tab) Embargoed until 2027-08-01

  10. Repurposing large pretrained diffusion models for unsupervised visual understanding and efficient adaptation

    Large pretrained text-conditioned image generation models learn a compositional and structured latent representation of visual concepts, showcasing their rich understanding of the world through their ability to generate diverse, coherent images. These models link text descriptions to visual …

    ubc Repository record for Repurposing large pretrained diffusion models for unsupervised visual understanding and efficient adaptation (opens in a new tab) Download PDF for Repurposing large pretrained diffusion models for unsupervised visual understanding and efficient adaptation (opens in a new tab)

  11. Neural Rendering Techniques for Photo-realistic Image Generation and Novel View Synthesis

    Recent advances in deep generative models have enabled computers to imagine and generate fictional images from any given distribution of images. Techniques like Generative Adversarial Networks (GANs) and image-to-image (I2I) translation can generate images by mapping a random noise or an input …

    maryland Repository record for Neural Rendering Techniques for Photo-realistic Image Generation and Novel View Synthesis (opens in a new tab)

  12. Evaluation of Information Access Systems in the Generative Era

    … access technologies, including neural retrieval models and generative information-seeking systems, has outpaced traditional evaluation methodologies, exposing fundamental gaps in assessing their effectiveness. Existing evaluation frameworks struggle to adapt, particularly in the presence of …

    waterloo Repository record for Evaluation of Information Access Systems in the Generative Era (opens in a new tab)

  13. Towards Multimodal Interactive Intelligence

    … has been made in multimodal generative AI models. However, these models still have limitations. For example, they struggle when handling multimodal data and multi-turn interactions. One reason is the lack of training data for these problems. The research community lacks multimodal data on …

    washington Repository record for Towards Multimodal Interactive Intelligence (opens in a new tab)

  14. Supervision and Data Dynamics in Vision Across Recognition and Generation Landscapes

    … and data dynamics across recognition and generation landscapes. Generative and discriminative modeling form important pillars in computer vision. Depending on the task techniques to better learn and utilize the data and labels can change. Through this work we investigate different tasks …

    maryland Repository record for Supervision and Data Dynamics in Vision Across Recognition and Generation Landscapes (opens in a new tab)

  15. Bringing GANs to Medieval Times: Manuscript Translation Models

    … new knowledge from existing knowledge. These models aim to learn patterns from input data then use that knowledge to generate output data samples that plausibly appear to belong to the same set as the input data. Medieval manuscripts study has been an important research area in the humanities …

    gsu Repository record for Bringing GANs to Medieval Times: Manuscript Translation Models (opens in a new tab)