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 2 of 2 for “"multimodal generative model"”.

  1. Towards Robust and Controllable Generative Audio Separation

    … conditions. This dissertation investigates generative modeling paradigms for controllable, robust, and perceptually-aligned audio separation, and proposes a unified framework that spans separation, correction, and evaluation. To improve controllability and robustness, we first study modern …

    jhu Repository record for Towards Robust and Controllable Generative Audio Separation (opens in a new tab)

  2. Knowledge-Centric Multimodal Intelligence: Understanding, Reasoning, and Generation

    Generative multimodal foundation models now handle a wide range of tasks spanning understanding, reasoning, and generation. Yet the knowledge they draw on at inference time is bounded by what their finite parameters memorized during training, leading to fabricated content, missed low-frequency …

    vt Repository record for Knowledge-Centric Multimodal Intelligence: Understanding, Reasoning, and Generation (opens in a new tab)