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 6 of 6 for “"Masked Diffusion"”.

  1. Understanding theoretical and empirical foundations of diffusion models

    … that have emerged over the past decade, diffusion models emerged as a powerful and principled framework, achieving state-of-the-art performance for continuous domains such as images and offering advantages like non-sequential reasoning and inference efficiency in discrete domains like …

    texas Repository record for Understanding theoretical and empirical foundations of diffusion models (opens in a new tab)

  2. Block-wise KV caching for uniform diffusion language models

    Diffusion language models offer a parallel alternative to autoregressive generation: rather than predicting tokens left-to-right, they iteratively refine an entire sequence from noise in a fixed number of steps. (Austin et al., 2021; Hoogeboom et al., 2021). Among these, uniform diffusion models …

    texas Repository record for Block-wise KV caching for uniform diffusion language models (opens in a new tab)

  3. Probability and Representation in Neural Systems: Dynamics, Learning, and Computation

    … train token prediction and unmasking order in a masked diffusion language model with on-policy reinforcement learning, improving parallel-generation accuracy--efficiency tradeoffs. Part II of this dissertation examines how learning shapes the internal representations supporting those …

    washington Repository record for Probability and Representation in Neural Systems: Dynamics, Learning, and Computation (opens in a new tab)

  4. Structure in Prediction: Mapping Large Language Model Prediction to Symbolic Structure

    … the model’s objective (autoregressive vs. masked diffusion) and the sequential nature of the data. Together, these studies support a unifying principle: whether provided by the data representation, the training objective, or an external prior, structure governs the efficiency and …

    cornell Repository record for Structure in Prediction: Mapping Large Language Model Prediction to Symbolic Structure (opens in a new tab)

  5. Discrete Diffusion for Text Infilling

    … parallelizability and flexible control. Discrete diffusion models offer a promising alternative paradigm, leveraging iterative refinement and potentially enabling bidirectional context use, parallel generation, and flexible prompting. However, existing discrete text diffusion models typically …

    vt Repository record for Discrete Diffusion for Text Infilling (opens in a new tab)

  6. Gumbel distillation for parallel text generation

    The slow, sequential nature of autoregressive (AR) language models has driven the adoption of parallel decoding methods. However, these non-AR models often sacrifice generation quality as they struggle to model the complex joint distribution of token sequences. To narrow this performance gap, this …

    texas Repository record for Gumbel distillation for parallel text generation (opens in a new tab)