9 papers
Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster
Grigory Bartosh, Teodora Pandeva, Sushrut Karmalkar +1
Discrete diffusion models are a powerful class of generative models with strong performance across many domains. For efficiency, however, discrete diffusion typically parameterizes…
Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network
Grigory Bartosh, David Ruhe, Emiel Hoogeboom +3
Diffusion models achieve state-of-the-art generative performance but suffer from high computational costs during inference due to the repeated evaluation of a heavy neural network.…
Purrception: Variational Flow Matching for Vector-Quantized Image Generation
RÄzvan-Andrei MatiÅan, Vincent Tao Hu, Grigory Bartosh +6
We introduce Purrception, a variational flow matching approach for vector-quantized image generation that provides explicit categorical supervision while maintaining continuous tra…
Towards Latent Diffusion Suitable For Text
Nesta Midavaine, Christian A. Naesseth, Grigory Bartosh
Language diffusion models aim to improve sampling speed and coherence over autoregressive LLMs. We introduce Neural Flow Diffusion Models for language generation, an extension of N…
Variational Flow Matching for Graph Generation
Floor Eijkelboom, Grigory Bartosh, Christian Andersson Naesseth +2
We present a formulation of flow matching as variational inference, which we refer to as variational flow matching (VFM). Based on this formulation we develop CatFlow, a flow match…
SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations
Grigory Bartosh, Dmitry Vetrov, Christian A. Naesseth
The Latent Stochastic Differential Equation (SDE) is a powerful tool for time series and sequence modeling. However, training Latent SDEs typically relies on adjoint sensitivity me…