Diffusion and flow processes forget dependencies to define valid copulas then learn to remember them for density estimation and sampling, outperforming prior copula methods on complex datasets.
Discrete copula diffusion
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2025 3representative citing papers
Fast-dLLM adds reusable KV cache blocks and selective parallel decoding to diffusion LLMs, closing most of the speed gap with autoregressive models without retraining.
VADD augments masked diffusion models with an auxiliary recognition model and variational inference to implicitly model inter-dimensional correlations, yielding higher-quality samples than standard MDMs at low denoising step counts on toy data, images, and text.
citing papers explorer
-
Diffusion and Flow-based Copulas: Forgetting and Remembering Dependencies
Diffusion and flow processes forget dependencies to define valid copulas then learn to remember them for density estimation and sampling, outperforming prior copula methods on complex datasets.
-
Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
Fast-dLLM adds reusable KV cache blocks and selective parallel decoding to diffusion LLMs, closing most of the speed gap with autoregressive models without retraining.
-
Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modeling
VADD augments masked diffusion models with an auxiliary recognition model and variational inference to implicitly model inter-dimensional correlations, yielding higher-quality samples than standard MDMs at low denoising step counts on toy data, images, and text.