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.
Variational diffusion models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Adapting autoregressive models via continual pre-training yields diffusion language models from 127M to 7B parameters that outperform prior diffusion models and compete with their autoregressive counterparts on language, reasoning, and commonsense benchmarks.
Flow Matching is a generative modeling framework with mathematical foundations, design choices, extensions, and open-source PyTorch code for applications like image and text generation.
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.
-
Scaling Diffusion Language Models via Adaptation from Autoregressive Models
Adapting autoregressive models via continual pre-training yields diffusion language models from 127M to 7B parameters that outperform prior diffusion models and compete with their autoregressive counterparts on language, reasoning, and commonsense benchmarks.
-
Flow Matching Guide and Code
Flow Matching is a generative modeling framework with mathematical foundations, design choices, extensions, and open-source PyTorch code for applications like image and text generation.