We have 4 of 39 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Gumbel Straight Flow (GSF), a continuous flow map language model that leverages the noise-data coupling of a pretrained autoregressive language (AR) model, can outperform current few-step language generation baselines.
A stochastic few-step generator whose FID does not degrade as the sampling budget grows from 4 to 50 NFE, and the same recipe transfers to text-to-image generation.
Simplex Diffusion Models (SDMs) are proposed, a framework that lifts the diffusion process to the probability simplex to represent beliefs over categories and can carry uncertainty across denoising steps, which mitigates information collapse.
This paper learns the guidance schedule as a function of diffusion time, conditioning and the current noisy sample, in order to better align sampled images with the text prompt.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
